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 |
|---|---|---|
| 1 | Claude Sonnet 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 70.6% |
| 2 | Claude Sonnet 5.5Claude Code --bare · max · no internet · safeguards with default fallback· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 70.6% |
| 3 | Claude Fable 5.2· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 67.6% |
| 4 | Claude Opus 5.5· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 66.4% |
| 5 | Claude Opus 5.5Opus 5.5 System Card capability section · Claude Code --bare · xhigh · safeguards with fallback · 5 trials/task· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 66.4% |
| 6 | Kimi K3.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 65.7% |
| 7 | Claude Opus 5.5Opus 5.5 System Card capability section · Claude Code --bare · max · safeguards with fallback · 5 trials/task· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 64.8% |
| 8 | Claude Opus 5.5Terminal-Bench 4.0 official leaderboard · Claude Code · max effort · 95% CI ±3.1 · 8.0B tokens · $4.7k· Reported by Terminal-Bench / Stanford / Harbor / Laude Institute· via BenchBoard docs | 64.8% |
| 9 | Claude Sonnet 5.5Terminal-Bench 4.0 official leaderboard · Claude Code · max effort · 95% CI ±2.9 · 19.4B tokens · $7.3k· Reported by Terminal-Bench / Stanford / Harbor / Laude Institute· via BenchBoard docs | 61.8% |
| 10 | GPT-6 Astraadaptive 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. | 58.2% |
| 11 | GPT-6 AstraTerminal-Bench 4.0 official leaderboard · Codex · max effort · 95% CI ±2.8 · 1.5B tokens · $3.3k· Reported by Terminal-Bench / Stanford / Harbor / Laude Institute· via BenchBoard docs | 58.2% |
| 12 | GPT-6.1 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. | 58.2% |
| 13 | GPT-6.1 SolTerminal-Bench 4.0 official leaderboard · Codex · max effort · 95% CI ±3.1 · 1.5B tokens · $634.24· Reported by Terminal-Bench / Stanford / Harbor / Laude Institute· via BenchBoard docs | 58.2% |
| 14 | Claude Fable 5.1Harbor · 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. | 57.9% |
| 15 | Claude Fable 5.1Terminal-Bench 4.0 official leaderboard · Claude Code · max effort · 95% CI ±3.8 · 2.7B tokens · $6.2k· Reported by Terminal-Bench / Stanford / Harbor / Laude Institute· via BenchBoard docs | 57.9% |
| 16 | Claude Fable 5.1Terminal-Bench 4.0 official leaderboard · Claude Code · xhigh effort · 95% CI ±3.4 · 2.3B tokens · $4.9k· Reported by Terminal-Bench / Stanford / Harbor / Laude Institute· via BenchBoard docs | 57.9% |
| 17 | GPT-6 AstraCode · high effort · chart displays 57.9% (raw 57.8788%)· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 57.9% |
| 18 | GPT-6 AstraOpenAI launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 57.9% |
| 19 | GPT-6 AstraOpus 5.5 System Card capability section · Codex · high effort · OpenAI-reported· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 57.9% |
| 20 | GPT-6 AstraTerminal-Bench 4.0 official leaderboard · Codex · high effort · 95% CI ±3 · 1.2B tokens · $2.3k· Reported by Terminal-Bench / Stanford / Harbor / Laude Institute· via BenchBoard docs | 57.9% |
| 21 | GPT-6 AstraTerminal-Bench 4.0 official leaderboard · Codex · xhigh effort · 95% CI ±2.7 · 1.2B tokens · $2.4k· Reported by Terminal-Bench / Stanford / Harbor / Laude Institute· via BenchBoard docs | 57.9% |
| 22 | GPT-6 Astra· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 57.7% |
| 23 | GPT-6 AstraCode · x-high effort· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 57.6% |
| 24 | Gemini 4 Argon· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 57.4% |
| 25 | GPT-6 AstraCode · max effort· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 56.7% |
| 26 | Claude Fable 5.1System 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. | 56% |
| 27 | Claude Fable 5.1· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 55.8% |
| 28 | Claude Fable 5.1Fable · Anthropic launch setting· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 55.8% |
| 29 | Claude Fable 5.1Non-code · max effort· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 55.8% |
| 30 | Claude Fable 5.1OpenAI launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 55.8% |
| 31 | Claude Fable 5.1Opus 5.5 System Card capability section · Claude Code --bare · max· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 55.8% |
| 32 | Claude Fable 5.1Terminal-Bench 4.0 official leaderboard · Claude Code · high effort · 95% CI ±3.4 · 2.2B tokens · $4.0k· Reported by Terminal-Bench / Stanford / Harbor / Laude Institute· via BenchBoard docs | 54.5% |
| 33 | GPT-6 AstraTerminal-Bench 4.0 official leaderboard · Codex · medium effort · 95% CI ±2.7 · 1.1B tokens · $1.9k· Reported by Terminal-Bench / Stanford / Harbor / Laude Institute· via BenchBoard docs | 54.2% |
| 34 | Claude Fable 5.1Terminal-Bench 4.0 official leaderboard · Claude Code · medium effort · 95% CI ±3.4 · 1.6B tokens · $2.8k· Reported by Terminal-Bench / Stanford / Harbor / Laude Institute· via BenchBoard docs | 53.9% |
| 35 | Claude Opus 5Terminal-Bench 4.0 official leaderboard · Claude Code · xhigh effort · 95% CI ±3.2 · 6.9B tokens · $6.1k· Reported by Terminal-Bench / Stanford / Harbor / Laude Institute· via BenchBoard docs | 53.9% |
| 36 | GPT-6 AstraCode · medium effort· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 53.9% |
| 37 | Claude Opus 5Non-code · max effort· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 52.6% |
| 38 | Claude Opus 5OpenAI launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 52.6% |
| 39 | Claude Opus 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. | 52.3% |
| 40 | Claude Opus 5Opus 5.5 System Card capability section · Claude Code --bare · max· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 52.3% |
| 41 | Claude Opus 5System 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. | 52% |
| 42 | Muse Wonder 1.0· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 52% |
| 43 | Claude Opus 5· LLM Stats data | 51.8% |
| 44 | Claude Opus 5DeepSeek Harness / max effort· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 51.8% |
| 45 | Claude Opus 5DeepSeek 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. | 51.8% |
| 46 | Claude Opus 5Google Model Card· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 51.8% |
| 47 | Claude Opus 5Terminal-Bench 4.0 official leaderboard · Claude Code · max effort · 95% CI ±3.4 · 6.5B tokens · $6.0k· Reported by Terminal-Bench / Stanford / Harbor / Laude Institute· via BenchBoard docs | 51.8% |
| 48 | Claude Fable 5.1Non-code · x-high effort· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 51.3% |
| 49 | GPT-6 AstraTerminal-Bench 4.0 official leaderboard · Codex · low effort · 95% CI ±2.8 · 889.8M tokens · $1.6k· Reported by Terminal-Bench / Stanford / Harbor / Laude Institute· via BenchBoard docs | 50.6% |
| 50 | Claude Opus 5Terminal-Bench 4.0 official leaderboard · Claude Code · high effort · 95% CI ±3.7 · 5.5B tokens · $4.7k· Reported by Terminal-Bench / Stanford / Harbor / Laude Institute· via BenchBoard docs | 50.3% |
Showing 1–50 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