Leaderboard
Terminal-Bench
46 models scored · metric: success rate. Prices are the cheapest listed across all serving providers. Pts/$ = score ÷ blended price (3×input + output) / 4 — how much score each dollar buys.
Best value · top 5 by pts per dollar
- 1.DeepSeek V4 Flash 0731788
- 2.Laguna XS 2.1500
- 3.GPT-5.6 Luna376
- 4.Step 3.7 Flash143
- 5.LongCat-2.0135
| # | Model | Score | Best in /M | Best out /M | Pts / $ | Context |
|---|---|---|---|---|---|---|
| 🥇 | GPT-5.6 Solopenai | 88.8 | $2.50 | $15 | 15.8 | 1.05M |
| 🥈 | Kimi K3moonshotai | 88.3 | $2.50 | $13.50 | 16.8 | 1.05M |
| 🥉 | Claude Fable 5anthropic | 88 | $10 | $50 | 4.4 | 1M |
| 4 | GPT-5.6 Terraopenai | 87.4 | $1 | $6 | 38.8 | 1.05M |
| 5 | Gemini 3.7 Flashgoogle | 85.8 | $0.375 | $1.88 | 114 | 1.05M |
| 6 | GPT-5.6 Lunaopenai | 84.7 | $0.1 | $0.6 | 376 | 1.05M |
| 7 | GPT-5.5openai | 84.1 | $4.55 | $27.27 | 8.2 | 1.05M |
| 8 | Grok 4.5xai | 83.3 | $2 | $6 | 27.8 | 500K |
| 9 | DeepSeek V4 Flash 0731deepseek | 82.7 | $0.08 | $0.18 | 788 | 1M |
| 10 | GPT-5.5openai | 82.7 | $4.55 | $27.27 | 8.1 | 1.05M |
| 11 | GLM-5.2zhipuai | 82.7 | $1.40 | $4.40 | 38.5 | 1M |
| 12 | GLM-5.2zhipuai | 81 | $1.40 | $4.40 | 37.7 | 1M |
| 13 | Claude Sonnet 5anthropic | 80.4 | $2 | $10 | 20.1 | 1M |
| 14 | Muse Spark 1.1meta | 80 | $1.25 | $4.25 | 40.0 | 1M |
| 15 | GPT-5.5openai | 78.2 | $4.55 | $27.27 | 7.6 | 1.05M |
| 16 | Gemini 3.6 Flashgoogle | 78 | $0.75 | $3.75 | 52.0 | 1.05M |
| 17 | Gemini 3.5 Flashgoogle | 76.2 | $1.50 | $9 | 22.6 | 1.05M |
| 18 | GPT-5.5openai | 75.8 | $4.55 | $27.27 | 7.4 | 1.05M |
| 19 | GPT-5.4openai | 75.1 | $2.20 | $14 | 14.6 | 1.05M |
| 20 | Claude Opus 4.8anthropic | 74.6 | $5 | $25 | 7.5 | 1M |
| 21 | Claude Opus 4.7anthropic | 73.8 | $5 | $25 | 7.4 | 1M |
| 22 | GPT-5.5openai | 73.4 | $4.55 | $27.27 | 7.2 | 1.05M |
| 23 | Claude Opus 4.7anthropic | 71.4 | $5 | $25 | 7.1 | 1M |
| 24 | LongCat-2.0meituan | 70.8 | $0.3 | $1.20 | 135 | 1M |
| 25 | Claude Opus 4.7anthropic | 70.6 | $5 | $25 | 7.1 | 1M |
| 26 | Gemini 3.1 Pro Previewgoogle | 70.3 | $2 | $12 | 15.6 | 1.05M |
| 27 | Claude Opus 4.6anthropic | 70.2 | $5 | $25 | 7.0 | 1M |
| 28 | GPT-5.4openai | 69.8 | $2.20 | $14 | 13.6 | 1.05M |
| 29 | Qwen3.7 Maxalibaba | 69.7 | $2.50 | $7.50 | 18.6 | 1M |
| 30 | Gemini 3.1 Pro Previewgoogle | 68.3 | $2 | $12 | 15.2 | 1.05M |
| 31 | Claude Sonnet 4.6anthropic | 67 | $3 | $15 | 11.2 | 1M |
| 32 | Claude Opus 4.7anthropic | 66.1 | $5 | $25 | 6.6 | 1M |
| 33 | MiniMax-M3minimax | 66 | $0.3 | $1.20 | 126 | 512K |
| 34 | GLM-5.1zhipuai | 65.1 | $1.40 | $4.40 | 30.3 | 200K |
| 35 | DeepSeek V4 Prodeepseek | 64.7 | $0.435 | $0.87 | 119 | 1M |
| 36 | GPT-5.4openai | 64.7 | $2.20 | $14 | 12.6 | 1.05M |
| 37 | Kimi K2.6moonshotai | 64.3 | $0.5 | $2.60 | 62.7 | 262K |
| 38 | Claude Sonnet 4.6anthropic | 63.1 | $3 | $15 | 10.5 | 1M |
| 39 | GPT-5.4 miniopenai | 60 | $0.68 | $4 | 39.7 | 400K |
| 40 | Step 3.7 Flashstepfun | 59.6 | $0.185 | $1.11 | 143 | 256K |
| 41 | Nemotron 3 Ultra 550B A55Bnvidia | 56.4 | $0.5 | $2.20 | 61.0 | 1M |
| 42 | Gemini 3.5 Flash Litegoogle | 54 | $0.3 | $2.50 | 63.5 | 1.05M |
| 43 | Muse Glimmer 30Bmeta | 51.7 | $0.3 | $1.10 | 103 | 131K |
| 44 | MiniMax-M2.7minimax | 51.1 | $0.3 | $1.20 | 97.3 | 205K |
| 45 | GPT-5.4 nanoopenai | 46.3 | $0.18 | $1.10 | 113 | 400K |
| 46 | Laguna XS 2.1poolside | 37.5 | $0.06 | $0.12 | 500 | 262K |
Cheapest scorer: Laguna XS 2.1 at $0.06 input /M.