Benchmark
Terminal-Bench 2.0 · Terminus-2
Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages. Higher is better.
- Models measured
- 25
- Scores recorded
- 44
- Sources
- 1
- IQ weight
- No weight published
Score distribution
- 58.1%
- Mean
- 57.8%
- Median
- 10.3%
- Std dev
- 46.4%
- 10th percentile
- 70.3%
- 90th percentile
- 37.1%
- Min
Leaderboard
| # | Model | Score |
|---|---|---|
| 1 | GPT 5.5xhigh· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 82.7% |
| 2 | GPT-5.3 CodexOpenAI GPT-5.4 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 77.3% |
| 3 | GPT-5.3 Codexxhigh· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 77.3% |
| 4 | GPT 5.4OpenAI GPT-5.4 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 75.1% |
| 5 | Qwen3.7 PlusQwen3.7-Plus release · Harbor/Terminus-2 · 5h · 12 CPU/24 GB · temp 1.0 · top_p 0.95 · top_k 20 · max_tokens 80K · 256K · avg@5· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 70.3% |
| 6 | Qwen3.7 MaxQwen3.7-Max release · Harbor/Terminus-2 · 5h · 12 CPU/24 GB · temp 1.0 · top_p 0.95 · top_k 20 · max_tokens 80K · 256K · avg@5· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 69.7% |
| 7 | Claude Opus 4.7Harbor · Terminus-2 · thinking disabled · 89 tasks · avg@5· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 69.4% |
| 8 | GLM 5.1GLM-5.1 official release table · best self-reported · Claude Code· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 69% |
| 9 | Gemini 3.1 Pro PreviewTerminus-2· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 68.5% |
| 10 | Kimi K2.6Kimi K2.6 official benchmark table · thinking · temp 1.0 · top_p 1.0 · 262,144 context · Terminus-2 · JSON parser · preserve thinking · avg@10· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 66.7% |
| 11 | Claude Opus 4.6Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 65.4% |
| 12 | GPT 5.2Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 64.7% |
| 13 | GLM 5.1GLM-5.1 official release table · Terminus-2· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 63.5% |
| 14 | GPT 5.2OpenAI GPT-5.4 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 62.2% |
| 15 | Qwen3.6 PlusQwen official release table · thinking mode unless benchmark requires otherwise · Harbor/Terminus-2 · 3h · 32 CPU/48GB · 256K · five-run mean· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 61.6% |
| 16 | GLM 5GLM-5 official release table · Claude Code 2.1.14 · Z.ai verified set · five-run mean· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 61.1% |
| 17 | GLM 5GLM-5 official release table · Terminus-2 · Z.ai verified set· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 60.7% |
| 18 | Claude Opus 4.5Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 59.8% |
| 19 | Qwen3.6 27BQwen official release table · thinking mode unless benchmark requires otherwise · Harbor/Terminus-2 · 3h · 32 CPU/48GB · 256K · five-run mean· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 59.3% |
| 20 | Claude Opus 4.5Harbor · Terminus-2 · 128K thinking budget · 1,335 trials· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 59.3% |
| 21 | Claude Sonnet 4.6Terminus-2 · max effort · no thinking · 5 runs· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 59.1% |
| 22 | Claude Opus 4.5Harbor · Terminus-2 · 64K thinking budget · 2,225 trials· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 57.8% |
| 23 | DeepSeek V4 FlashDeepSeek V4 official model card · Think Max· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 56.9% |
| 24 | DeepSeek V4 FlashDeepSeek V4 official model card · Think High· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 56.6% |
| 25 | Gemini 3 Pro PreviewOpus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 56.2% |
| 26 | GLM 5GLM-5 official release table · Claude Code 2.1.14 · original set · five-run mean· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 56.2% |
| 27 | GLM 5GLM-5 official release table · Terminus-2 · original set· Reported by Z.ai· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 56.2% |
| 28 | Gemini 3 Pro PreviewGemini 3 Pro Model Card · results as of November 2025 · Terminus-2· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 54.2% |
| 29 | Qwen3.6 FlashQwen3.6-35B-A3B official model card · hosted API name Qwen3.6-Flash· Reported by Alibaba Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 51.5% |
| 30 | Claude Sonnet 4.5Opus 4.6 System Card capability summary · adaptive thinking · max effort · default sampling · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 51% |
| 31 | Step 3.5 FlashStep 3.5 Flash official headline table · vanilla· Reported by StepFun· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 51% |
| 32 | Step 3.5 FlashStep 3.5 technical report · Table 16 · baseline · avg@8· Reported by StepFun· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 51% |
| 33 | Kimi K2.5· Reported by Moonshot AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 50.8% |
| 34 | Step 3.5 FlashStep 3.5 technical report · Table 16 · 100 rounds · avg@8· Reported by StepFun· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 50.4% |
| 35 | Claude Sonnet 4.5launch-page setting· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 50% |
| 36 | Step 3.5 FlashStep 3.5 technical report · Table 16 · 2-hour timeout · avg@8· Reported by StepFun· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 49.7% |
| 37 | DeepSeek V4 FlashDeepSeek V4 official model card · Non-Think· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 49.1% |
| 38 | Step 3.5 FlashStep 3.5 technical report · Table 16 · 16K output · avg@8· Reported by StepFun· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 48% |
| 39 | Gemini 3 FlashTerminus-2 harness · public leaderboard· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 47.6% |
| 40 | DeepSeek V3.2Thinking mode · temperature 1.0 · 128K context · Claude Code framework· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 46.4% |
| 41 | Step 3.5 FlashStep 3.5 technical report · Table 16 · 16K output without pruning · avg@8· Reported by StepFun· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 45.2% |
| 42 | Claude Haiku 4.5launch-page setting· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 41% |
| 43 | DeepSeek V3.2Non-thinking mode · temperature 1.0 · 128K context · Terminus framework· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 39.3% |
| 44 | DeepSeek V3.2Non-thinking mode · temperature 1.0 · 128K context · Claude Code framework· Reported by DeepSeek· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 37.1% |