Terminal Bench 2.1 · 2.1

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Qwen Claude Code avg@10,5h timeout,131072 output; comparators best published across harnesses.

Cited comparator result; see the benchmark footnote.

Comparison limit: The Qwen card cites an external leaderboard or release report for this comparator; it is not a new Qwen evaluation.

Qwen/Qwen3.8-2.4T-A95B · Performance table: Terminal Bench 2.1 · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Qwen Claude Code avg@10,5h timeout,131072 output; comparators best published across harnesses.

First-party reported result.

Qwen/Qwen3.8-2.4T-A95B · Performance table: Terminal Bench 2.1 · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Qwen Claude Code avg@10,5h timeout,131072 output; comparators best published across harnesses.

Cited comparator result; see the benchmark footnote.

Comparison limit: The Qwen card cites an external leaderboard or release report for this comparator; it is not a new Qwen evaluation. The source states that Fable 5 results may involve fallback execution; an exact configuration is not established.

Qwen/Qwen3.8-2.4T-A95B · Performance table: Terminal Bench 2.1 · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Qwen Claude Code avg@10,5h timeout,131072 output; comparators best published across harnesses.

Cited comparator result; see the benchmark footnote.

Comparison limit: The Qwen card cites an external leaderboard or release report for this comparator; it is not a new Qwen evaluation.

Qwen/Qwen3.8-2.4T-A95B · Performance table: Terminal Bench 2.1 · reviewed 2026-09-12

Source benchmark-specific methodology; Qwen benchmark effort unspecified, GPT-5.6 Sol max per table header. Max in Qwen model names is not a reported effort setting. Comparator settings and source citations as documented in the model card. Qwen Claude Code avg@10,5h timeout,131072 output; comparators best published across harnesses.

Cited comparator result; see the benchmark footnote.

Comparison limit: The Qwen card cites an external leaderboard or release report for this comparator; it is not a new Qwen evaluation.

Qwen/Qwen3.8-2.4T-A95B · Performance table: Terminal Bench 2.1 · reviewed 2026-09-12

DeepSeek updated 0813/0731 release evaluation table; tool/harness settings per model card.

First-party reported result.

Comparison limit: The source labels this column Fable-5 (w/ fallback); it does not establish standalone Fable 5 performance. Retained as published evidence, excluded from comparable ranking inputs.

deepseek-ai/DeepSeek-V4-Pro-0813 · Performance table: Terminal Bench 2.1 · reviewed 2026-09-12

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

First-party reported result.

Comparison limit: The source column includes fallback execution without a documented exact effort.

zai-org/GLM-5.3 · Performance table: Terminal Bench 2.1 · reviewed 2026-09-12

DeepSeek updated 0813/0731 release evaluation table; tool/harness settings per model card.

First-party reported result.

deepseek-ai/DeepSeek-V4-Pro-0813 · Performance table: Terminal Bench 2.1 · reviewed 2026-09-12

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

First-party reported result.

zai-org/GLM-5.3 · Performance table: Terminal Bench 2.1 · reviewed 2026-09-12

DeepSeek updated 0813/0731 release evaluation table; tool/harness settings per model card.

First-party reported result.

deepseek-ai/DeepSeek-V4-Pro-0813 · Performance table: Terminal Bench 2.1 · reviewed 2026-09-12

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

First-party reported result.

zai-org/GLM-5.3 · Performance table: Terminal Bench 2.1 · reviewed 2026-09-12

DeepSeek updated 0813/0731 release evaluation table; tool/harness settings per model card.

First-party reported result.

deepseek-ai/DeepSeek-V4-Pro-0813 · Performance table: Terminal Bench 2.1 · reviewed 2026-09-12

NVIDIA evaluation harness/settings per benchmark in model card; comparator scores are NVIDIA-reported under that protocol.

First-party reported result. Original cell: 59.3 The linked public reproduction recipe names Terminal Bench 2.0, while this card labels 2.1. Recipe settings are not transferred across that unresolved version mismatch.

nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · Performance table: Terminal Bench 2.1 · reviewed 2026-09-06

DeepSeek updated 0813/0731 release evaluation table; tool/harness settings per model card.

First-party reported result.

deepseek-ai/DeepSeek-V4-Pro-0813 · Performance table: Terminal Bench 2.1 · reviewed 2026-09-12

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

First-party reported result.

zai-org/GLM-5.3 · Performance table: Terminal Bench 2.1 · reviewed 2026-09-12

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

First-party reported result.

zai-org/GLM-5.3 · Performance table: Terminal Bench 2.1 · reviewed 2026-09-12

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

First-party reported result.

zai-org/GLM-5.3 · Performance table: Terminal Bench 2.1 · reviewed 2026-09-12

DeepSeek updated 0813/0731 release evaluation table; tool/harness settings per model card.

First-party reported result.

deepseek-ai/DeepSeek-V4-Pro-0813 · Performance table: Terminal Bench 2.1 · reviewed 2026-09-12

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

First-party reported result.

zai-org/GLM-5.3 · Performance table: Terminal Bench 2.1 · reviewed 2026-09-12

NVIDIA evaluation harness/settings per benchmark in model card; comparator scores are NVIDIA-reported under that protocol.

First-party reported result. Original cell: 67.2 The linked public reproduction recipe names Terminal Bench 2.0, while this card labels 2.1. Recipe settings are not transferred across that unresolved version mismatch.

nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · Performance table: Terminal Bench 2.1 · reviewed 2026-09-06

NVIDIA evaluation harness/settings per benchmark in model card; comparator scores are NVIDIA-reported under that protocol.

First-party reported result. Original cell: 55.5 The linked public reproduction recipe names Terminal Bench 2.0, while this card labels 2.1. Recipe settings are not transferred across that unresolved version mismatch.

nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · Performance table: Terminal Bench 2.1 · reviewed 2026-09-06

NVIDIA evaluation harness/settings per benchmark in model card; comparator scores are NVIDIA-reported under that protocol.

First-party reported result. Original cell: 56.4 The linked public reproduction recipe names Terminal Bench 2.0, while this card labels 2.1. Recipe settings are not transferred across that unresolved version mismatch.

nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · Performance table: Terminal Bench 2.1 · reviewed 2026-09-06

GLM-5.3 release table; benchmark-specific harness and reasoning configurations in Evaluation Details.

First-party reported result.

zai-org/GLM-5.3 · Performance table: Terminal Bench 2.1 · reviewed 2026-09-12

NVIDIA evaluation harness/settings per benchmark in model card; comparator scores are NVIDIA-reported under that protocol.

First-party reported result. Original cell: 49.9 The linked public reproduction recipe names Terminal Bench 2.0, while this card labels 2.1. Recipe settings are not transferred across that unresolved version mismatch.

nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16 · Performance table: Terminal Bench 2.1 · reviewed 2026-09-06