Grok-4.5

Data updated 12 Sept 2026

13 published benchmark measures · 5 benchmark families contribute across 3 task areas. 3 capability estimates available in the full profile. See all results ↓ · Compare published benchmarks →

Model evidence summary

Choose a configuration

A model-wide score would mix effort settings. This page summarizes published evidence; only identified configurations receive leaderboard ranks.

Compare measured configurations →

The capability chart summarizes evidence across reported settings, not a runnable configuration or a leaderboard rank.

Performance profile

Capabilities

Adjusted comparison score · 0–100

Filled points are supported; hollow points are preliminary. Lines stop at unknown capabilities. Exact values and sources follow below.

Agentic2 families · 0 with independent evidence · Supported30.8

2 core families; 3 direct opponents across 3 labs.

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: 28.9–35.0; 2/11 scenarios unsupported. Without one publisher: 26.6–37.5; 1/15 unsupported. Smoothing check: 26.0–36.6; 0/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage; source sensitivity still requires inspection. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

Apex Agents: 0.0 observed win share
xAI · Source 1
GDPval: 0.0 observed win share
xAI · Source 1

Hard reasoningNo comparable evidenceUnknown

0 core families; 0 direct opponents across 0 labs. No admitted core comparisons

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: No supported estimate; 7/7 scenarios unsupported. Without one publisher: No supported estimate; 16/16 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

Coding2 families · 1 with independent evidence · Supported25.2

2 core families; 27 direct opponents across 9 labs.

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: 25.2–33.1; 2/7 scenarios unsupported. Without one publisher: 23.0–33.0; 1/20 unsupported. Smoothing check: 21.4–31.4; 0/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts improved on neutral predictions within evaluated coverage. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

DeepSWE: 17.6 observed win share
deepswe.datacurve.ai, xAI · Source 1 Source 2
Terminal-Bench: 0.0 observed win share
xAI · Source 1

Human pref1 families · 1 with independent evidence · Supported40.1

1 core families; 114 direct opponents across 19 labs.

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: No supported estimate; 1/1 scenarios unsupported. Without one publisher: No supported estimate; 1/1 unsupported. Smoothing check: 34.1–45.1; 0/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: cross-family and cross-publisher predictions could not be evaluated from the available comparison network. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

Human preference (Arena): 87.7 observed win share
lmarena.ai · Source 1

KnowledgeNo comparable evidenceUnknown

0 core families; 0 direct opponents across 0 labs. No admitted core comparisons

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: No supported estimate; 4/4 scenarios unsupported. Without one publisher: No supported estimate; 5/5 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: almost no publisher-held-out comparisons remained estimable. Cross-source validity is unresolved. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

MultimodalNo comparable evidenceUnknown

0 core families; 0 direct opponents across 0 labs. No admitted core comparisons

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: No supported estimate; 8/8 scenarios unsupported. Without one publisher: No supported estimate; 8/8 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: limited publisher-held-out coverage. Cross-source validity is unresolved. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

Long contextNo comparable evidenceUnknown

0 core families; 0 direct opponents across 0 labs. No admitted core comparisons

Estimated against the same complete panel: gpt-5.6-sol claude-opus-4-8 gemini-3.1-pro . Indirect comparisons assume performance can be summarized by one strength within this capability.

Refit without one family: No supported estimate; 5/5 scenarios unsupported. Without one publisher: No supported estimate; 5/5 unsupported. Smoothing check: No supported estimate; 3/3 unsupported. These are sensitivity checks, not confidence intervals.

Audit: family and publisher holdouts underperformed neutral predictions. Treat this as an exploratory estimate. Validation audit.

Matched family win shares below describe source evidence; they are not averaged to produce the adjusted score.

Scores estimate outcomes against a shared reference panel; they are not accuracy percentages. Sparse or disconnected evidence cannot qualify an overall profile. Open a capability to inspect its evidence.

Compare 3 effort levels across 42 benchmark/harness combinations →

Reported effort · Not specified

Settings reported in this model's published benchmark results, including results outside the aggregate. Effort names are provider-specific. These are not API defaults or equal compute budgets.

Not specified: 15 observations

Mixed settings means multiple settings occur in the evidence. Best across efforts means the source selected its best reported result across settings; it does not mean Max. Unspecified settings stay unknown. This model-summary chart combines reported settings. The leaderboard keeps identified configurations separate and excludes unknown effort.

Inspect each result and its source ↓ · Download effort evidence

Compare capability profiles →

Score contributions and missing evidence

5 contributing families across 3 capabilities. Fixed reference panels do not change when the catalog expands.

Capability is fitted jointly across families. Capability estimates below describe different task areas; their weighted sum is not the Capability score.

Results without reviewed compatibility or a reference match remain in the raw evidence below. Coverage counts only contributing results.

Model information & shareable badge

Lab: xAI
Catalog status: active
Availability: Public provider catalog; account and region restrictions may apply
Family: Grok 4
Released: —
Context: 500,000 tokens
License: proprietary
Model card: https://docs.x.ai/developers/pricing
Default Capability family coverage: /badge/grok-4.5.svg

Benchmark scores & sources

Original results, evaluation harnesses, and evidence behind this model.

Benchmark	Bucket	Score	Harness	Evidence	Source-recorded date
AA Intelligence Index · source release snapshot; version not specified	Supporting evidence	56 index points Reported settings & source Grok High; GPT-5.6 Sol Max; Fable 5 Max. Competitor figures from developer cards/public leaderboards as selected by xAI. First-party reported result; comparator results retain the source evaluation setup. Grok 4.6 launch evaluations · Performance table · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
AA-Briefcase (Elo) · source release snapshot; version not specified	Supporting evidence	1313 Reported settings & source Grok High; GPT-5.6 Sol Max; Fable 5 Max. Competitor figures from developer cards/public leaderboards as selected by xAI. First-party reported result; comparator results retain the source evaluation setup. Grok 4.6 launch evaluations · Performance table · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
APEX-Agents · source release snapshot; version not specified	Agentic	47.1% Reported settings & source Grok High; GPT-5.6 Sol Max; Fable 5 Max. Competitor figures from developer cards/public leaderboards as selected by xAI. First-party reported result; comparator results retain the source evaluation setup. Grok 4.6 launch evaluations · Performance table · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
APEX-SWE · source release snapshot; version not specified	Supporting evidence	53.6% Reported settings & source Grok High; GPT-5.6 Sol Max; Fable 5 Max. Competitor figures from developer cards/public leaderboards as selected by xAI. First-party reported result; comparator results retain the source evaluation setup. Grok 4.6 launch evaluations · Performance table · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
CursorBench v3.2 · v3.2	Supporting evidence	66.7% Reported settings & source Grok High; GPT-5.6 Sol Max; Fable 5 Max. Competitor figures from developer cards/public leaderboards as selected by xAI. First-party reported result; comparator results retain the source evaluation setup. Grok 4.6 launch evaluations · Performance table · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
DeepSWE v1.1	Coding	53.8%	DeepSWE v1.1 reported Effort: Not specified contributes to capability	official board	2026-09-03
DeepSWE v1.1 · v1.1	Coding	54% Reported settings & source Grok High; GPT-5.6 Sol Max; Fable 5 Max. Competitor figures from developer cards/public leaderboards as selected by xAI. First-party reported result; comparator results retain the source evaluation setup. Grok 4.6 launch evaluations · Performance table · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
FrontierCode v1.1 Extended · v1.1	Supporting evidence	56.6% Reported settings & source Grok High; GPT-5.6 Sol Max; Fable 5 Max. Competitor figures from developer cards/public leaderboards as selected by xAI. First-party reported result; comparator results retain the source evaluation setup. Grok 4.6 launch evaluations · Performance table · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
GDPval-AA v2 (Elo) · source release snapshot; version not specified	Agentic	1526 Reported settings & source Grok High; GPT-5.6 Sol Max; Fable 5 Max. Competitor figures from developer cards/public leaderboards as selected by xAI. First-party reported result; comparator results retain the source evaluation setup. Grok 4.6 launch evaluations · Performance table · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
Harvey LAB (Vals) · source release snapshot; version not specified	Supporting evidence	12.9% Reported settings & source Grok High; GPT-5.6 Sol Max; Fable 5 Max. Competitor figures from developer cards/public leaderboards as selected by xAI. First-party reported result; comparator results retain the source evaluation setup. Grok 4.6 launch evaluations · Performance table · reviewed 2026-09-06	Published configuration Effort: Not specified	lab self-report Supporting evidence outside the reviewed capability core	Reviewed 2026-09-06
LMArena Text Arena	Human pref	1469	LMArena Text Effort: Not specified contributes to capability	official board	2026-09-11
Terminal-Bench v3.0 · v3.0	Coding	15.7% Reported settings & source Grok High; GPT-5.6 Sol Max; Fable 5 Max. Competitor figures from developer cards/public leaderboards as selected by xAI. First-party reported result; comparator results retain the source evaluation setup. Grok 4.6 launch evaluations · Performance table · reviewed 2026-09-06	Published configuration Effort: Not specified contributes to capability	lab self-report	Reviewed 2026-09-06
VulcanBench v3	Supporting evidence	91.3%	VulcanBench v3 bare-bones API · Report 07 · high Effort: Not specified	official board Supporting evidence outside the reviewed capability core	2026-07-12
VulcanBench v3	Supporting evidence	82.6%	VulcanBench v3 bare-bones API · Report 07 · low Effort: Not specified	official board Supporting evidence outside the reviewed capability core	2026-07-12
VulcanBench v3	Supporting evidence	91.3%	VulcanBench v3 bare-bones API · Report 07 · medium Effort: Not specified	official board Supporting evidence outside the reviewed capability core	2026-07-12
ARC-AGI-2	Hard reasoning	—	—	—	—
GDPval-AA	Agentic	—	—	—	—
GPQA Diamond	Hard reasoning	—	—	—	—
Humanity's Last Exam	Hard reasoning	—	—	—	—
LiveCodeBench	Coding	—	—	—	—
MMLU-Pro	Knowledge	—	—	—	—
OSWorld-Verified	Agentic	—	—	—	—
SWE-bench Pro	Agentic	—	—	—	—
SWE-bench Verified	Agentic	—	—	—	—
Terminal-Bench 2.1	Agentic	—	—	—	—