| GPT-5.5 | 84.7% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5.5 | 83.1% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5.5 | 82.2% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5.5 | 82.0% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5.4 | 81.8% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
Claude Opus 4.7Anthropic · Unknown effort | 80.2% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Gemini 3.1 Pro | 80.2% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
Claude Opus 4.6Anthropic · Unknown effort | 79.8% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5.3-Codex | 78.4% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Gemini 3.1 Pro | 78.4% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| Gemini 3.1 Pro | 78.4% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5.3-Codex | 77.3% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
Claude Opus 4.6Anthropic · Unknown effort | 76.4% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5.3-Codex | 75.8% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5.3-Codex | 75.7% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
Claude Opus 4.6Anthropic · Unknown effort | 75.3% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5.3-Codex | 75.1% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Gemini 3.1 Pro | 74.8% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
Claude Opus 4.6Anthropic · Unknown effort | 74.7% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5.3-Codex | 74.6% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
Claude Opus 4.6Anthropic · Unknown effort | 72.1% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
Claude Opus 4.6Anthropic · Unknown effort | 71.9% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5.3-Codex | 71.5% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5.3-Codex | 70.3% | Source not stated | Epoch AI via Epoch AI | — |
| Claude Opus 4.6 | 69.9% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
Claude Opus 4.6Anthropic · Unknown effort | 69.9% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Gemini 3 Pro | 69.4% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5.3-Codex | 69.1% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
Claude Opus 4.6Anthropic · Unknown effort | 66.9% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
Claude Opus 4.6Anthropic · Unknown effort | 66.5% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5.2-Codex | 66.5% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5.5 | 66.1% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Gemini 3 Pro | 65.2% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5.2 | 64.9% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5.2 | 64.9% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| GPT-5.3-Codex | 64.7% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Gemini 3 Flash | 64.3% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
Claude Opus 4.5Anthropic · Unknown effort | 63.1% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Claude Opus 4.5 | 63.1% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
Claude Opus 4.6Anthropic · Unknown effort | 62.9% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5.2 | 62.9% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5.2 | 62.9% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| Gemini 3 Pro | 62.2% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Gemini 3 Pro | 62.2% | Source not stated | Epoch AI via Epoch AI | — |
| Gemini 3 Pro | 61.8% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5.1-Codex-Mini | 61.6% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Gemini 3 Pro | 61.1% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5.2 | 60.7% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5.1-Codex-Max | 60.4% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Gemini 3.1 Pro | 59.4% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
Claude Opus 4.5Anthropic · Unknown effort | 59.1% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Claude Opus 4.5 | 59.1% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
Claude Opus 4.5Anthropic · Unknown effort | 58.4% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
Claude Opus 4.6Anthropic · Unknown effort | 58.0% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5.1-Codex | 57.8% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
Claude Opus 4.5Anthropic · Unknown effort | 57.8% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5.1-Codex | 57.8% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Grok 4.20 | 57.3% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Grok 4.20 | 57.3% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Gemini 3 Pro | 56.9% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Gemini 3 Pro | 56.0% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
Claude Opus 4.5Anthropic · Unknown effort | 54.3% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5.2 | 54.0% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5.1-Codex | 53.5% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
Claude Sonnet 4.6Anthropic · Unknown effort | 53.4% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Claude Sonnet 4.6 | 53.4% | Source not stated | Epoch AI via Epoch AI | — |
| GLM-5 | 52.4% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
Claude Opus 4.5Anthropic · Unknown effort | 52.1% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
Claude Opus 4.5Anthropic · Unknown effort | 51.9% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
Claude Opus 4.5Anthropic · Unknown effort | 51.7% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Gemini 3 Flash | 51.7% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Gemini 3 Flash | 51.0% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| GPT-5 | 49.6% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5 | 49.6% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| GPT-5.1 | 47.6% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| GPT-5.1 | 47.6% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| GPT-5.1 | 47.6% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Gemini 3 Flash | 47.4% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
Claude Sonnet 4.5Anthropic · Unknown effort | 46.5% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| MiniMax-M2.7 | 45.1% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5-Codex | 44.3% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5-Codex | 44.3% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| GPT-5 | 43.8% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5 | 43.8% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| GPT-5-Codex | 43.4% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5-Codex | 43.4% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| Kimi K2.5 | 43.2% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
Claude Sonnet 4.5Anthropic · Unknown effort | 43.1% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5.1-Codex-Mini | 43.1% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5.1-Codex-Mini | 43.1% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| MiniMax-M2.7 | 42.9% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
Claude Sonnet 4.5Anthropic · Unknown effort | 42.8% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Claude Sonnet 4.5 | 42.8% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
Claude Sonnet 4.5Anthropic · Unknown effort | 42.7% | Source not stated | Epoch AI via Epoch AI | — |
Claude Sonnet 4.5Anthropic · Unknown effort | 42.7% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| MiniMax-M2.5 | 42.7% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Claude Sonnet 4.5 | 42.6% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
Claude Sonnet 4.5Anthropic · Unknown effort | 42.6% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
Claude Sonnet 4.5Anthropic · Unknown effort | 42.5% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Claude Sonnet 4.5 | 42.5% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| MiniMax-M2.5 | 42.2% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5-Codex | 41.3% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5-Codex | 41.3% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| Claude Sonnet 4.5 | 40.1% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
Claude Sonnet 4.5Anthropic · Unknown effort | 40.1% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| DeepSeek-V3.2 | 39.6% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Claude Opus 4.1 | 38.0% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
Claude Opus 4.1Anthropic · Unknown effort | 38.0% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Claude Opus 4.1 | 36.9% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| GPT-5.1-Codex | 36.9% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
Claude Opus 4.1Anthropic · Unknown effort | 36.9% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5.1-Codex | 36.9% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| MiniMax-M2.1 | 36.6% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Kimi K2 Thinking | 35.7% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Kimi K2 Thinking | 35.7% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
Claude Haiku 4.5Anthropic · Unknown effort | 35.5% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5 | 35.2% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| GPT-5 | 35.2% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Claude Opus 4.1 | 35.1% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
Claude Opus 4.1Anthropic · Unknown effort | 35.1% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
Claude Opus 4.1Anthropic · Unknown effort | 34.8% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5 mini | 34.8% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Claude Opus 4.1 | 34.8% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| GPT-5 mini | 34.8% | Source not stated | Epoch AI via Epoch AI | — |
| GPT-5 | 33.9% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5 | 33.9% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| GLM-4.7 | 33.4% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GLM-4.7 | 33.3% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Gemini 2.5 Pro | 32.6% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Gemini 2.5 Pro | 32.6% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| GPT-5 mini | 31.9% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| GPT-5 mini | 31.9% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| MiniMax-M2 | 30.0% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
Claude Haiku 4.5Anthropic · Unknown effort | 29.8% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Claude Haiku 4.5 | 29.8% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| GPT-5 mini | 29.2% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| MiniMax-M2.1 | 29.2% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5 mini | 29.2% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
Claude Haiku 4.5Anthropic · Unknown effort | 28.3% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Claude Haiku 4.5 | 28.3% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
Claude Haiku 4.5Anthropic · Unknown effort | 27.5% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Claude Haiku 4.5 | 27.5% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| Grok 4 | 27.2% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| Grok 4 | 27.2% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Qwen3-Coder-480B-A35B-Instruct | 27.2% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Gemini 2.5 Pro | 26.1% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| Gemini 2.5 Pro | 26.1% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Grok Code Fast 1 | 25.8% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Grok Code Fast 1 | 25.8% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| Grok 4 | 25.4% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| Qwen3-Coder-480B-A35B-Instruct | 25.4% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| Grok 4 | 25.4% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Qwen3-Coder-480B-A35B-Instruct | 25.4% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GLM-4.6 | 24.5% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GLM-4.6 | 24.5% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| GPT-5 mini | 24.0% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5 mini | 24.0% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| Qwen3-Coder-480B-A35B-Instruct | 23.9% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| Qwen3-Coder-480B-A35B-Instruct | 23.9% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Grok 4 | 23.1% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Grok 4 | 23.1% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| Qwen3.6-35B-A3B | 23.0% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5 mini | 22.2% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5 mini | 22.2% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| GPT-5 nano | 21.8% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Gemini 2.5 Pro | 19.6% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| Gemini 2.5 Pro | 19.6% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| gpt-oss-120b | 18.7% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| gpt-oss-120b | 18.7% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Gemini 2.5 Flash | 17.1% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| Gemini 2.5 Flash | 17.1% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Gemini 2.5 Flash | 16.9% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| Gemini 2.5 Flash | 16.9% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Gemini 2.5 Flash | 16.4% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Gemini 2.5 Pro | 16.4% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Gemini 2.5 Flash | 16.4% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| Gemini 2.5 Pro | 16.4% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| Gemini 2.5 Flash | 15.4% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Gemini 2.5 Flash | 15.4% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| gpt-oss-120b | 14.2% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| Grok Code Fast 1 | 14.2% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| gpt-oss-120b | 14.2% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Grok Code Fast 1 | 14.2% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
Claude Haiku 4.5Anthropic · Unknown effort | 13.9% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Claude Haiku 4.5 | 13.9% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| GPT-5 nano | 11.5% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| GPT-5 nano | 11.5% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5 nano | 9.9% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| GPT-5 nano | 9.9% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| Qwen3.5-9B | 9.2% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5 nano | 7.9% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| GPT-5 nano | 7.9% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| GPT-5 nano | 7.0% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| GPT-5 nano | 7.0% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| gpt-oss-20b | 3.4% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| gpt-oss-20b | 3.4% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |
| gpt-oss-20b | 3.1% | Third party | Terminal-Bench v2 Leaderboard via Epoch AI | — |
| gpt-oss-20b | 3.1% | Third party | https://www.tbench.ai/leaderboard/terminal-bench/2.0 via Epoch AI | — |