Benchmark
Terminal-Bench 4.0
Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages. Higher is better.
- Models and systems measured
- 44
- Scores recorded
- 136
- Sources
- 2
- IQ weight
- 1.66
Score distribution
- 40%
- Mean
- 41.8%
- Median
- 16.8%
- Std dev
- 14.5%
- 10th percentile
- 57.9%
- 90th percentile
- 1%
- Min
This benchmark has a weight of 1.66 for chat models, measured over 35 models. The weight is how much it counts toward llminfo IQ. We measure it from the data, not from the raw scores.
Leaderboard
| # | Model or system | Score |
|---|---|---|
| 51 | GPT-6.1 Terra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 50.3% |
| 52 | GPT-6 AstraCode · low effort· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 49.7% |
| 53 | Claude Fable 5.1Non-code · high effort· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 49.4% |
| 54 | GPT-6 Soladaptive thinking · max effort · default sampling · 5-trial mean · context ≤1M unless noted · public leaderboard · Codex CLI · max· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 49.4% |
| 55 | GPT-6 SolTerminal-Bench 4.0 official leaderboard · Codex · max effort · 95% CI ±3.2 · 5.0B tokens · $1.5k· Reported by Terminal-Bench / Stanford / Harbor / Laude Institute· via BenchBoard docs | 49.4% |
| 56 | ERNIE 5.5 Flash Preview· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 46.5% |
| 57 | Claude Opus 5Terminal-Bench 4.0 official leaderboard · Claude Code · medium effort · 95% CI ±3.8 · 3.7B tokens · $3.2k· Reported by Terminal-Bench / Stanford / Harbor / Laude Institute· via BenchBoard docs | 44.8% |
| 58 | Claude Fable 5· LLM Stats data | 44.5% |
| 59 | Claude Fable 5Non-code · max effort· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 44.5% |
| 60 | Claude Fable 5OpenAI launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 44.5% |
| 61 | Claude Fable 5Terminal-Bench 4.0 official leaderboard · Claude Code · max effort · 95% CI ±3.8 · 3.8B tokens · $7.3k· Reported by Terminal-Bench / Stanford / Harbor / Laude Institute· via BenchBoard docs | 44.5% |
| 62 | Claude Fable 5.1Non-code · medium effort· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 43.4% |
| 63 | Claude Fable 5.1Terminal-Bench 4.0 official leaderboard · Claude Code · low effort · 95% CI ±3.6 · 1.3B tokens · $2.4k· Reported by Terminal-Bench / Stanford / Harbor / Laude Institute· via BenchBoard docs | 43.3% |
| 64 | DeepSeek V4.1 Flash 1017· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 42.3% |
| 65 | DeepSeek V4.1 Flash 1017DeepSeek 1017 first-party evaluation · reasoning effort, candidate sampling, exact run count, and unspecified harnesses not published · Claude Code harness · provider run, distinct from maintainer leaderboard· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 42.3% |
| 66 | Claude Fable 5Anthropic Fable/Mythos 5.1 launch table· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 42% |
| 67 | Claude Fable 5System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted · Fable· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 42% |
| 68 | GLM 5.3· LLM Stats data | 41.8% |
| 69 | GLM 5.3Terminal-Bench 4.0 official leaderboard · Claude Code · max effort · 95% CI ±3.2 · 8.7B tokens · $2.7k· Reported by Terminal-Bench / Stanford / Harbor / Laude Institute· via BenchBoard docs | 41.8% |
| 70 | Mistral Large 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 41% |
| 71 | Claude Fable 5.1Non-code · low effort· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 40.2% |
| 72 | GPT-5.6 SolDeepSeek Harness / max effort· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 39.9% |
| 73 | GPT-5.6 SolDeepSeek V4.1 launch chart · exact public value · setting not further specified· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 39.9% |
| 74 | Claude Haiku 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 39.2% |
| 75 | Claude Haiku 5.5Claude Code --bare · max · 10 trials/task · no internet · safeguards stop trial· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 39.2% |
| 76 | LongCat 2.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 38.5% |
| 77 | MiniMax M3.1 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 38.1% |
| 78 | MiniMax M3.1 FlashMiniMax M3.1 Flash official-weights model-card run · reasoning effort, sampling, and run count not stated for this benchmark · Codex 0.149.1 · provider-reported result, distinct from maintainer leaderboard· Reported by MiniMax· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 38.1% |
| 79 | Grok 4.7· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 38% |
| 80 | Grok 4.7Harbor · provider harness · task success rate · xhigh effort· Reported by SpaceXAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 38% |
| 81 | GLM 5.3DeepSeek Harness / max effort· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 37.9% |
| 82 | GLM 5.3DeepSeek V4.1 launch chart · exact public value · setting not further specified· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 37.9% |
| 83 | Grok 4.7Grok Build · release-page value· Reported by SpaceXAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 37.6% |
| 84 | Grok 4.7Terminal-Bench 4.0 official leaderboard · Grok Build · xhigh effort · 95% CI ±3.5 · 5.5B tokens · $3.68k (cost partial: 324/330 trials)· Reported by Terminal-Bench / Stanford / Harbor / Laude Institute· via BenchBoard docs | 37.6% |
| 85 | GPT-5.6 Sol· LLM Stats data | 37.3% |
| 86 | GPT-5.6 SolAnthropic Fable/Mythos 5.1 launch table· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 37.3% |
| 87 | GPT-5.6 SolGoogle Model Card· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 37.3% |
| 88 | GPT-5.6 SolHarbor · provider harness · task success rate · max effort· Reported by SpaceXAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 37.3% |
| 89 | GPT-5.6 SolNon-code · max effort · chart displays 37.3% (raw 37.2727%)· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 37.3% |
| 90 | GPT-5.6 SolOpenAI launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 37.3% |
| 91 | GPT-5.6 SolTerminal-Bench 4.0 official leaderboard · Codex · max effort · 95% CI ±3.8 · 4.4B tokens · $2.5k· Reported by Terminal-Bench / Stanford / Harbor / Laude Institute· via BenchBoard docs | 37.3% |
| 92 | GPT-5.6 SolSystem Card capability summary · adaptive thinking · max effort · default sampling · 5 trials · context ≤1M unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 37% |
| 93 | GLM 5.3 FlashTerminal-Bench 4.0 official leaderboard · Claude Code · none effort · 95% CI ±3.5 · 2.9B tokens · $118.74· Reported by Terminal-Bench / Stanford / Harbor / Laude Institute· via BenchBoard docs | 35.8% |
| 94 | MiMo V2.6 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 34.9% |
| 95 | Claude Opus 5Terminal-Bench 4.0 official leaderboard · Claude Code · low effort · 95% CI ±3.9 · 2.7B tokens · $2.4k· Reported by Terminal-Bench / Stanford / Harbor / Laude Institute· via BenchBoard docs | 34.8% |
| 96 | DeepSeek V4.1 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 31.2% |
| 97 | DeepSeek V4.1 FlashDeepSeek Harness / max effort· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 31.2% |
| 98 | DeepSeek V4.1 FlashDeepSeek V4.1 launch chart · exact public value · setting not further specified· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 31.2% |
| 99 | MiMo V2.6 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 28.8% |
| 100 | GPT-5.6 SolNon-code · x-high effort· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 28.5% |
Showing 51–100 of 133 results.
Not ranked
The source marks these results as descriptive, not capability scores, so we list them by name instead of ranking them.
| Model or system | Score |
|---|---|
| Grok 4.6Harbor · provider harness · task success rate · high effort· Reported by SpaceXAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 20.3% |
| Grok 4.6Terminal-Bench 4.0 official leaderboard · Grok Build · high effort · 95% CI ±3.1 · 4.0B tokens · $3.6k· Reported by Terminal-Bench / Stanford / Harbor / Laude Institute· via BenchBoard docs | 20.3% |
| Qwen3.8 Max 0902Terminal-Bench 4.0 official leaderboard · Claude Code · max effort · 95% CI ±3.8 · 3.0B tokens · $4.6k· Reported by Terminal-Bench / Stanford / Harbor / Laude Institute· via BenchBoard docs | 27% |
Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links. · Data by LLM Stats