Benchmark
Terminal-Bench 2.1
Agentic benchmarks measure how well models carry out tasks that take several steps. Scores are percentages. Higher is better.
- Models and systems measured
- 64
- Scores recorded
- 159
- Sources
- 3
- IQ weight
- 2.76
Score distribution
- 75.3%
- Mean
- 82.7%
- Median
- 17.2%
- Std dev
- 56.4%
- 10th percentile
- 88.8%
- 90th percentile
- 2.9%
- Min
This benchmark has a weight of 2.76 for chat models, measured over 53 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 |
|---|---|---|
| 101 | GPT 5.5Gemini 3.5 Flash Model Card · May 2026 · Terminus-2· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 78.2% |
| 102 | GPT 5.5Opus 4.8 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 78.2% |
| 103 | Gemini 3.6 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 78% |
| 104 | Gemini 3.6 FlashGemini 3.6 Flash Model Card · July 2026 · Terminus-2· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 78% |
| 105 | Muse Spark Open· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 76.4% |
| 106 | Muse Spark Open 816B A42B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 76.4% |
| 107 | Gemini 3.5 FlashGemini 3.5 Flash Model Card · May 2026 · Terminus-2· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 76.2% |
| 108 | Gemini 3.5 FlashGemini 3.6 Flash Model Card · July 2026 · Terminus-2· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 76.2% |
| 109 | Muse Spark 1.1mini-swe-agent· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 76.2% |
| 110 | Claude Opus 4.8Opus 4.8 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 74.6% |
| 111 | Qwen3.7 MaxQwen表:Qwen 采用 Claude Code avg@10、5h、max_tokens 131072;友商取公开最高分· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 74.5% |
| 112 | Gemini 3.1 Pro PreviewGemini 3.6 Flash Model Card · July 2026 · Terminus-2· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 73.8% |
| 113 | Qwen 3.8 27B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 73% |
| 114 | Qwen 3.8 27BQwen3.8-27B model card · published setting· Reported by Qwen· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 73% |
| 115 | Hy3 (Deep Infra)· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 71.7% |
| 116 | Hy3 (Deep Infra)Hy3 official Benchmark Appendix · highest reasoning tier unless noted · Terminus-2 · XML parser · 4-hour timeout · 500 episodes· Reported by Tencent Hunyuan· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 71.7% |
| 117 | Inkling 2 Mini· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 71.6% |
| 118 | Doubao Seed 2.1 Pro· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 71% |
| 119 | LongCat 2.0· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claim | 70.8% |
| 120 | Gemini 3.1 Pro PreviewGemini CLI· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 70.7% |
| 121 | Gemini 3.1 Pro PreviewOpenAI GPT-5.6 launch table· Reported by OpenAI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 70.7% |
| 122 | Gemini 3.1 Pro PreviewGemini 3.5 Flash Model Card · May 2026 · Terminus-2· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 70.3% |
| 123 | Gemini 3.1 Pro Previewhigh · 89 tasks · bash-only · pass@1 · five-attempt mean· Reported by Meta, Meta Superintelligence Labs· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 70.3% |
| 124 | Gemini 3.1 Pro PreviewOpus 4.8 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 70.3% |
| 125 | Laguna S 2.1· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 70.2% |
| 126 | Doubao Seed 2.1 Turbo· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 67.6% |
| 127 | Claude Sonnet 4.6mini-SWE-agent · high effort · Sonnet 5 card infrastructure· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 67% |
| 128 | NVIDIA Nemotron 3.5 Super VL 120B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 66.7% |
| 129 | Claude Opus 4.7Gemini 3.5 Flash Model Card · May 2026 · Terminus-2· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 66.1% |
| 130 | Claude Opus 4.7Opus 4.8 System Card capability summary · adaptive thinking · max effort · 5 trials unless noted· Reported by Anthropic· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 66.1% |
| 131 | MiniMax M3· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 66% |
| 132 | MiniMax M3official model-page overview figure· Reported by MiniMax· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 66% |
| 133 | MiniMax M3Terminus 2 · 8C16G · 2h timeout · 128K max output· Reported by MiniMax Research· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 66% |
| 134 | Inkling Small· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 64.7% |
| 135 | Inkling FP4· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 63.8% |
| 136 | MAI-Code-1.1-Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 62.9% |
| 137 | Step 3.7 Flash· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 59.5% |
| 138 | Step 3.7 FlashStep 3.7 Flash official README/figure· Reported by StepFun· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 59.5% |
| 139 | Gemini 3 FlashGemini 3.5 Flash Model Card · May 2026 · Terminus-2· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 58% |
| 140 | Ling 3.0 Flash· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 57% |
| 141 | Solar Pro 4· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 57% |
| 142 | Nemotron 3 Ultra· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 56.4% |
| 143 | Nemotron 3 UltraNeMo Evaluator SDK · official table· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 56.4% |
| 144 | Gemini 3.5 Flash Lite· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 54% |
| 145 | Muse Glimmer 30B· Hugging Face Official Benchmarks data· Reported by the model's developer. The source relaying it did not verify it. claimValues from 2 sources
| 51.7% |
| 146 | Muse Glimmer 30BTerminus 2 · high reasoning· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 51.7% |
| 147 | Nemotron 3.5 Lightning 30B A3Bagentic-coding figure · Mini-SWE-Agent v2.4.5 · unmodified system prompt · standard harness configuration· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 29.7% |
| 148 | Granite 4.2 30B· LLM Stats data· Reported by the model's developer. The source relaying it did not verify it. claim | 29.2% |
| 149 | Nemotron 3.5 Lightning 30B A3Bagentic-coding figure · OpenCode v1.17.8 · unmodified system prompt · standard harness configuration· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 29.1% |
| 150 | Nemotron 3.5 Lightning 30B A3Bagentic-coding figure · Claude v2.1.126 · unmodified system prompt · standard harness configuration· Reported by NVIDIA· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 29% |
Showing 101–150 of 158 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 |
|---|---|
| Muse Spark (version unspecified)Meta Model API · highest effort · version unspecified · 89 tasks · bash-only · pass@1 · five-attempt mean· Reported by Meta, Meta Superintelligence Labs· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it. | 67.3% |
Data credits: Data by LLM Stats · Hugging Face official benchmark leaderboards; licence varies by benchmark · 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.