Compare published benchmarks

Use the full performance tables published with model releases. Compare the tests both models have, with category weights you choose.

These are publisher-reported configurations. A shared table does not establish equal inference budgets or an independent reproduction. Win share measures the fraction of weighted test outcomes won, not the size or statistical significance of an advantage.

First model

Second model

Published evaluation

Category weights

Agentic Hard reasoning Coding Human pref Knowledge Multimodal Long context

Weights are relative. Categories share the total; each benchmark family shares its category equally. Related versions and settings divide their family’s allocation.

Include different reported configurations, with their differences shown

GPT-5.4 and Gemini 3.1 Pro

Weighted benchmark win share: GPT-5.4 100.0% · Gemini 3.1 Pro -0.0%. Based on 7 shared measures out of 32 reported measures for this pair. Exact reported ties contribute half to each model.

Missing results never count as losses. Changing the source, selected models or weights can change the comparison. This is not a global model rank.

Explore all benchmark coverage · Compare the calibrated benchmark set · Download all observations

Benchmark	GPT-5.4	Gemini 3.1 Pro	Comparison
HLE-Full (w/ tools) Agentic · Higher is better	52.1% Reported settings & source Kimi K2.6 card, HLE-Full (w/ tools). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, HLE-Full (w/ tools), column 3 · reviewed 2026-09-12	51.4% Reported settings & source Kimi K2.6 card, HLE-Full (w/ tools). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, HLE-Full (w/ tools), column 5 · reviewed 2026-09-12	Cited comparator requires original evaluation provenance; not a new matched run.
BrowseComp Agentic · Higher is better	82.7% Reported settings & source Kimi K2.6 card, BrowseComp. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, BrowseComp, column 3 · reviewed 2026-09-12	85.9% Reported settings & source Kimi K2.6 card, BrowseComp. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, BrowseComp, column 5 · reviewed 2026-09-12	Cited comparator requires original evaluation provenance; not a new matched run.
BrowseComp (Agent Swarm) Agentic · Higher is better	82.7% Reported settings & source Kimi K2.6 card, BrowseComp (Agent Swarm). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, BrowseComp (Agent Swarm), column 3 · reviewed 2026-09-12	85.9% Reported settings & source Kimi K2.6 card, BrowseComp (Agent Swarm). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, BrowseComp (Agent Swarm), column 5 · reviewed 2026-09-12	Cited comparator requires original evaluation provenance; not a new matched run.
DeepSearchQA (f1-score) Agentic · Higher is better	78.6% Reported settings & source Kimi K2.6 card, DeepSearchQA (f1-score). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, DeepSearchQA (f1-score), column 3 · reviewed 2026-09-12	81.9% Reported settings & source Kimi K2.6 card, DeepSearchQA (f1-score). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, DeepSearchQA (f1-score), column 5 · reviewed 2026-09-12	Cited comparator requires original evaluation provenance; not a new matched run.
DeepSearchQA (accuracy) Agentic · Higher is better	63.7% Reported settings & source Kimi K2.6 card, DeepSearchQA (accuracy). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, DeepSearchQA (accuracy), column 3 · reviewed 2026-09-12	60.2% Reported settings & source Kimi K2.6 card, DeepSearchQA (accuracy). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, DeepSearchQA (accuracy), column 5 · reviewed 2026-09-12	Cited comparator requires original evaluation provenance; not a new matched run.
Toolathlon Agentic · Higher is better	54.6% Reported settings & source Kimi K2.6 card, Toolathlon. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, Toolathlon, column 3 · reviewed 2026-09-12	48.8% Reported settings & source Kimi K2.6 card, Toolathlon. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, Toolathlon, column 5 · reviewed 2026-09-12	Cited comparator requires original evaluation provenance; not a new matched run.
MCPMark Agentic · Higher is better	62.5% Reported settings & source Kimi K2.6 card, MCPMark. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Kimi K2.6 official model card · Evaluation Results table, MCPMark, column 3 · reviewed 2026-09-12	55.9% Reported settings & source Kimi K2.6 card, MCPMark. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Kimi K2.6 official model card · Evaluation Results table, MCPMark, column 5 · reviewed 2026-09-12	GPT-5.4 · 50.0% weight
Claw Eval (pass^3) Agentic · Higher is better	60.3% Reported settings & source Kimi K2.6 card, Claw Eval (pass^3). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, Claw Eval (pass^3), column 3 · reviewed 2026-09-12	57.8% Reported settings & source Kimi K2.6 card, Claw Eval (pass^3). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, Claw Eval (pass^3), column 5 · reviewed 2026-09-12	Cited comparator requires original evaluation provenance; not a new matched run.
Claw Eval (pass@3) Agentic · Higher is better	78.4% Reported settings & source Kimi K2.6 card, Claw Eval (pass@3). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, Claw Eval (pass@3), column 3 · reviewed 2026-09-12	82.9% Reported settings & source Kimi K2.6 card, Claw Eval (pass@3). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, Claw Eval (pass@3), column 5 · reviewed 2026-09-12	Cited comparator requires original evaluation provenance; not a new matched run.
APEX-Agents Agentic · Higher is better	33.3% Reported settings & source Kimi K2.6 card, APEX-Agents. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, APEX-Agents, column 3 · reviewed 2026-09-12	32% Reported settings & source Kimi K2.6 card, APEX-Agents. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, APEX-Agents, column 5 · reviewed 2026-09-12	Cited comparator requires original evaluation provenance; not a new matched run.
OSWorld-Verified Agentic · Higher is better	75% Reported settings & source Kimi K2.6 card, OSWorld-Verified. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, OSWorld-Verified, column 3 · reviewed 2026-09-12	No result	Missing result
Terminal-Bench 2.0 (Terminus-2) Coding · Higher is better	65.4% Reported settings & source Kimi K2.6 card, Terminal-Bench 2.0 (Terminus-2). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Coding: average of ten runs; Terminal uses Terminus2 preserve-thinking; SWE uses in-house SWE-agent. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Kimi K2.6 official model card · Evaluation Results table, Terminal-Bench 2.0 (Terminus-2), column 3 · reviewed 2026-09-12	68.5% Reported settings & source Kimi K2.6 card, Terminal-Bench 2.0 (Terminus-2). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Coding: average of ten runs; Terminal uses Terminus2 preserve-thinking; SWE uses in-house SWE-agent. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, Terminal-Bench 2.0 (Terminus-2), column 5 · reviewed 2026-09-12	Cited comparator requires original evaluation provenance; not a new matched run.
SWE-Bench Pro Coding · Higher is better	57.7% Reported settings & source Kimi K2.6 card, SWE-Bench Pro. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Coding: average of ten runs; Terminal uses Terminus2 preserve-thinking; SWE uses in-house SWE-agent. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, SWE-Bench Pro, column 3 · reviewed 2026-09-12	54.2% Reported settings & source Kimi K2.6 card, SWE-Bench Pro. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Coding: average of ten runs; Terminal uses Terminus2 preserve-thinking; SWE uses in-house SWE-agent. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, SWE-Bench Pro, column 5 · reviewed 2026-09-12	Cited comparator requires original evaluation provenance; not a new matched run.
SWE-Bench Multilingual Coding · Higher is better	No result	76.9% Reported settings & source Kimi K2.6 card, SWE-Bench Multilingual. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Coding: average of ten runs; Terminal uses Terminus2 preserve-thinking; SWE uses in-house SWE-agent. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Kimi K2.6 official model card · Evaluation Results table, SWE-Bench Multilingual, column 5 · reviewed 2026-09-12	Missing result
SWE-Bench Verified Coding · Higher is better	No result	80.6% Reported settings & source Kimi K2.6 card, SWE-Bench Verified. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Coding: average of ten runs; Terminal uses Terminus2 preserve-thinking; SWE uses in-house SWE-agent. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, SWE-Bench Verified, column 5 · reviewed 2026-09-12	Missing result
SciCode Coding · Higher is better	56.6% Reported settings & source Kimi K2.6 card, SciCode. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Coding: average of ten runs; Terminal uses Terminus2 preserve-thinking; SWE uses in-house SWE-agent. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, SciCode, column 3 · reviewed 2026-09-12	58.9% Reported settings & source Kimi K2.6 card, SciCode. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Coding: average of ten runs; Terminal uses Terminus2 preserve-thinking; SWE uses in-house SWE-agent. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, SciCode, column 5 · reviewed 2026-09-12	Cited comparator requires original evaluation provenance; not a new matched run.
OJBench (python) Coding · Higher is better	No result	70.7% Reported settings & source Kimi K2.6 card, OJBench (python). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Coding: average of ten runs; Terminal uses Terminus2 preserve-thinking; SWE uses in-house SWE-agent. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, OJBench (python), column 5 · reviewed 2026-09-12	Missing result
LiveCodeBench (v6) Coding · Higher is better	No result	91.7% Reported settings & source Kimi K2.6 card, LiveCodeBench (v6). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Coding: average of ten runs; Terminal uses Terminus2 preserve-thinking; SWE uses in-house SWE-agent. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, LiveCodeBench (v6), column 5 · reviewed 2026-09-12	Missing result
HLE-Full Hard reasoning · Higher is better	39.8% Reported settings & source Kimi K2.6 card, HLE-Full. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Reasoning: 98304 generation tokens; HLE full set. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, HLE-Full, column 3 · reviewed 2026-09-12	44.4% Reported settings & source Kimi K2.6 card, HLE-Full. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Reasoning: 98304 generation tokens; HLE full set. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, HLE-Full, column 5 · reviewed 2026-09-12	Cited comparator requires original evaluation provenance; not a new matched run.
AIME 2026 Hard reasoning · Higher is better	99.2% Reported settings & source Kimi K2.6 card, AIME 2026. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Reasoning: 98304 generation tokens; HLE full set. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, AIME 2026, column 3 · reviewed 2026-09-12	98.3% Reported settings & source Kimi K2.6 card, AIME 2026. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Reasoning: 98304 generation tokens; HLE full set. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, AIME 2026, column 5 · reviewed 2026-09-12	Cited comparator requires original evaluation provenance; not a new matched run.
HMMT 2026 (Feb) Hard reasoning · Higher is better	97.7% Reported settings & source Kimi K2.6 card, HMMT 2026 (Feb). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Reasoning: 98304 generation tokens; HLE full set. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, HMMT 2026 (Feb), column 3 · reviewed 2026-09-12	94.7% Reported settings & source Kimi K2.6 card, HMMT 2026 (Feb). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Reasoning: 98304 generation tokens; HLE full set. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, HMMT 2026 (Feb), column 5 · reviewed 2026-09-12	Cited comparator requires original evaluation provenance; not a new matched run.
IMO-AnswerBench Hard reasoning · Higher is better	91.4% Reported settings & source Kimi K2.6 card, IMO-AnswerBench. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Reasoning: 98304 generation tokens; HLE full set. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, IMO-AnswerBench, column 3 · reviewed 2026-09-12	91% Reported settings & source Kimi K2.6 card, IMO-AnswerBench. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Reasoning: 98304 generation tokens; HLE full set. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Kimi K2.6 official model card · Evaluation Results table, IMO-AnswerBench, column 5 · reviewed 2026-09-12	Cited comparator requires original evaluation provenance; not a new matched run.
GPQA-Diamond Hard reasoning · Higher is better	92.8% Reported settings & source Kimi K2.6 card, GPQA-Diamond. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Reasoning: 98304 generation tokens; HLE full set. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, GPQA-Diamond, column 3 · reviewed 2026-09-12	94.3% Reported settings & source Kimi K2.6 card, GPQA-Diamond. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Reasoning: 98304 generation tokens; HLE full set. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, GPQA-Diamond, column 5 · reviewed 2026-09-12	Cited comparator requires original evaluation provenance; not a new matched run.
MMMU-Pro Multimodal · Higher is better	81.2% Reported settings & source Kimi K2.6 card, MMMU-Pro. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Vision: 98304 tokens, average of three runs; Python condition uses 65536 tokens per step, at most50steps. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, MMMU-Pro, column 3 · reviewed 2026-09-12	83% Reported settings & source Kimi K2.6 card, MMMU-Pro. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Vision: 98304 tokens, average of three runs; Python condition uses 65536 tokens per step, at most50steps. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Kimi K2.6 official model card · Evaluation Results table, MMMU-Pro, column 5 · reviewed 2026-09-12	Cited comparator requires original evaluation provenance; not a new matched run.
MMMU-Pro (w/ python) Multimodal · Higher is better	82.1% Reported settings & source Kimi K2.6 card, MMMU-Pro (w/ python). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Vision: 98304 tokens, average of three runs; Python condition uses 65536 tokens per step, at most50steps. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, MMMU-Pro (w/ python), column 3 · reviewed 2026-09-12	85.3% Reported settings & source Kimi K2.6 card, MMMU-Pro (w/ python). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Vision: 98304 tokens, average of three runs; Python condition uses 65536 tokens per step, at most50steps. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Kimi K2.6 official model card · Evaluation Results table, MMMU-Pro (w/ python), column 5 · reviewed 2026-09-12	Cited comparator requires original evaluation provenance; not a new matched run.
CharXiv (RQ) Multimodal · Higher is better	82.8% Reported settings & source Kimi K2.6 card, CharXiv (RQ). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Vision: 98304 tokens, average of three runs; Python condition uses 65536 tokens per step, at most50steps. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Kimi K2.6 official model card · Evaluation Results table, CharXiv (RQ), column 3 · reviewed 2026-09-12	80.2% Reported settings & source Kimi K2.6 card, CharXiv (RQ). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Vision: 98304 tokens, average of three runs; Python condition uses 65536 tokens per step, at most50steps. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Kimi K2.6 official model card · Evaluation Results table, CharXiv (RQ), column 5 · reviewed 2026-09-12	GPT-5.4 · 8.3% weight
CharXiv (RQ) (w/ python) Multimodal · Higher is better	90% Reported settings & source Kimi K2.6 card, CharXiv (RQ) (w/ python). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Vision: 98304 tokens, average of three runs; Python condition uses 65536 tokens per step, at most50steps. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Kimi K2.6 official model card · Evaluation Results table, CharXiv (RQ) (w/ python), column 3 · reviewed 2026-09-12	89.9% Reported settings & source Kimi K2.6 card, CharXiv (RQ) (w/ python). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Vision: 98304 tokens, average of three runs; Python condition uses 65536 tokens per step, at most50steps. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Kimi K2.6 official model card · Evaluation Results table, CharXiv (RQ) (w/ python), column 5 · reviewed 2026-09-12	GPT-5.4 · 8.3% weight
MathVision Multimodal · Higher is better	92% Reported settings & source Kimi K2.6 card, MathVision. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Vision: 98304 tokens, average of three runs; Python condition uses 65536 tokens per step, at most50steps. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Kimi K2.6 official model card · Evaluation Results table, MathVision, column 3 · reviewed 2026-09-12	89.8% Reported settings & source Kimi K2.6 card, MathVision. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Vision: 98304 tokens, average of three runs; Python condition uses 65536 tokens per step, at most50steps. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Kimi K2.6 official model card · Evaluation Results table, MathVision, column 5 · reviewed 2026-09-12	GPT-5.4 · 8.3% weight
MathVision (w/ python) Multimodal · Higher is better	96.1% Reported settings & source Kimi K2.6 card, MathVision (w/ python). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Vision: 98304 tokens, average of three runs; Python condition uses 65536 tokens per step, at most50steps. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Kimi K2.6 official model card · Evaluation Results table, MathVision (w/ python), column 3 · reviewed 2026-09-12	95.7% Reported settings & source Kimi K2.6 card, MathVision (w/ python). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Vision: 98304 tokens, average of three runs; Python condition uses 65536 tokens per step, at most50steps. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Kimi K2.6 official model card · Evaluation Results table, MathVision (w/ python), column 5 · reviewed 2026-09-12	GPT-5.4 · 8.3% weight
BabyVision Multimodal · Higher is better	49.7% Reported settings & source Kimi K2.6 card, BabyVision. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Vision: 98304 tokens, average of three runs; Python condition uses 65536 tokens per step, at most50steps. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, BabyVision, column 3 · reviewed 2026-09-12	51.6% Reported settings & source Kimi K2.6 card, BabyVision. Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Vision: 98304 tokens, average of three runs; Python condition uses 65536 tokens per step, at most50steps. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Cited from another official report; does not establish a new same-protocol evaluation. Comparison limit: Cited comparator requires original evaluation provenance; not a new matched run. Kimi K2.6 official model card · Evaluation Results table, BabyVision, column 5 · reviewed 2026-09-12	Cited comparator requires original evaluation provenance; not a new matched run.
BabyVision (w/ python) Multimodal · Higher is better	80.2% Reported settings & source Kimi K2.6 card, BabyVision (w/ python). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Vision: 98304 tokens, average of three runs; Python condition uses 65536 tokens per step, at most50steps. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Kimi K2.6 official model card · Evaluation Results table, BabyVision (w/ python), column 3 · reviewed 2026-09-12	68.3% Reported settings & source Kimi K2.6 card, BabyVision (w/ python). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Vision: 98304 tokens, average of three runs; Python condition uses 65536 tokens per step, at most50steps. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Kimi K2.6 official model card · Evaluation Results table, BabyVision (w/ python), column 5 · reviewed 2026-09-12	GPT-5.4 · 8.3% weight
V* (w/ python) Multimodal · Higher is better	98.4% Reported settings & source Kimi K2.6 card, V* (w/ python). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Vision: 98304 tokens, average of three runs; Python condition uses 65536 tokens per step, at most50steps. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Kimi K2.6 official model card · Evaluation Results table, V* (w/ python), column 3 · reviewed 2026-09-12	96.9% Reported settings & source Kimi K2.6 card, V* (w/ python). Thinking mode; temperature 1.0, top-p 1.0, context 262144. Comparator settings: GPT-5.4 xhigh, Opus4.6 max, Gemini3.1Pro high. See benchmark-specific footnotes. Only own K2.6 and starred re-evaluations can form new comparisons. Vision: 98304 tokens, average of three runs; Python condition uses 65536 tokens per step, at most50steps. Source SHA256 95db3be1d0473e482c7aa901f237ad7af8bb7929625a777b27428081bb8ea9f7. Own measurement or explicitly starred same-condition re-evaluation. Assess benchmark-specific protocol before admission. Kimi K2.6 official model card · Evaluation Results table, V* (w/ python), column 5 · reviewed 2026-09-12	GPT-5.4 · 8.3% weight