Best AI Models for Warp
Warp is an AI-powered terminal with built-in command suggestions and natural language to shell translation. Fast, cheap models with strong instruction following work best.
What Matters for Warp
Best Models for Warp
Top 15 by tool-optimized score
All Models Ranked for Warp (378 models)
Scored by: benchmark performance (90%) from MMLU, GPQA, HumanEval, SWE-bench, and 15+ standardized evaluations, with capabilities and context as tiebreakers (10%).
| # | Model | Score | Output $/M |
|---|---|---|---|
| 1 | MiMo-V2.5-Pro Arena Elo: 1467 | 89 | $0.870 |
| 2 | Muse Spark 1.1 Arena Elo: 1487 | 88 | $4.25 |
| 3 | Hy3 Arena Elo: 1453 | 88 | $0.528 |
| 4 | Gemma 4 31B Arena Elo: 1451 | 88 | $0.340 |
| 5 | GPT-5.6 Luna Pro | 87 | $0.600 |
| 6 | GPT-5.6 Luna Pro (batch) | 87 | $0.600 |
| 7 | GPT-5.6 Luna | 87 | $0.600 |
| 8 | GPT-5.6 Luna (batch) | 87 | $0.600 |
| 9 | MiMo-V2.5 Arena Elo: 1434 | 87 | $0.280 |
| 10 | Gemma 4 26B A4B Arena Elo: 1438 | 87 | $0.340 |
| 11 | Qwen3.8 Max Arena Elo: 1497 | 86 | $6.00 |
| 12 | Gemini 3.5 Flash Lite Arena Elo: 1459 | 86 | $2.50 |
| 13 | Qwen3.7 Plus Arena Elo: 1458 | 86 | $1.28 |
| 14 | Kimi K2.6 Arena Elo: 1461 | 86 | $2.44 |
| 15 | GLM 5.1 Arena Elo: 1468 | 86 | $2.99 |
| 16 | DeepSeek V3.2 Exp Arena Elo: 1423 | 86 | $0.410 |
| 17 | Llama 3.3 70B Instruct HumanEval: 88.4% | 86 | $0.320 |
| 18 | GPT-4o-mini HumanEval: 87.2% | 86 | $0.600 |
| 19 | Gemini 3.6 Flash Arena Elo: 1485 | 85 | $7.50 |
| 20 | Hy3 preview Arena Elo: 1412 | 85 | $0.210 |
| 21 | Gemma 4 31B (free) | 85 | Free |
| 22 | GLM 5 Arena Elo: 1457 | 85 | $2.55 |
| 23 | DeepSeek V3.1 Arena Elo: 1418 | 85 | $0.950 |
| 24 | Inkling Arena Elo: 1442 | 84 | $4.05 |
| 25 | MiniMax M3 Arena Elo: 1445 | 84 | $1.20 |
| 26 | Gemini 3.5 Flash Arena Elo: 1477 | 84 | $9.00 |
| 27 | Claude Opus 4.7 (batch) | 84 | $12.50 |
| 28 | Qwen3.6 Plus Arena Elo: 1443 | 84 | $1.95 |
| 29 | Qwen3.5 397B A17B Arena Elo: 1442 | 84 | $2.34 |
| 30 | GLM 4.7 Arena Elo: 1442 | 84 | $1.75 |
| 31 | GPT-5.2 Chat Arena Elo: 1476 | 84 | $14.00 |
| 32 | Inkling Small Arena Elo: 1431 | 83 | $1.20 |
| 33 | Grok 4.5 Arena Elo: 1468 | 83 | $6.00 |
| 34 | Claude Opus 4.8 (batch) | 83 | $12.50 |
| 35 | Grok 4.3 | 83 | $2.50 |
| 36 | Qwen3.6 Max Preview Arena Elo: 1460 | 83 | $6.16 |
| 37 | GLM 5V Turbo Arena Elo: 1433 | 83 | $4.00 |
| 38 | Grok 4.20 | 83 | $2.50 |
| 39 | Gemini 3.1 Flash Lite Preview Arena Elo: 1432 | 83 | $1.50 |
| 40 | Qwen3.5-Flash Arena Elo: 1397 | 83 | $0.260 |
| 41 | Step 3.5 Flash Arena Elo: 1394 | 83 | $0.300 |
| 42 | Gemini 3 Flash Preview (batch) | 83 | $1.50 |
| 43 | GPT-5.1-Codex-Mini | 83 | $2.00 |
| 44 | GLM 4.6 Arena Elo: 1425 | 83 | $2.00 |
| 45 | Claude Fable 5 (batch) | 82 | $25.00 |
| 46 | DeepSeek V4 Pro SWE-bench: 80.6% | 82 | $0.870 |
| 47 | Gemma 4 26B A4B (free) | 82 | Free |
| 48 | MiniMax M2.7 Arena Elo: 1416 | 82 | $1.08 |
| 49 | GPT-5.4 Nano (batch) | 82 | $0.625 |
| 50 | GPT-5.4 (batch) | 82 | $7.50 |
More Tool Rankings
Based on our analysis of coding benchmarks, capability matching, and pricing, MiMo-V2.5-Pro currently ranks #1 for Warp. Rankings are rebuilt as benchmark, pricing, and provider data refresh.
We score models using benchmark performance (90%) from LMArena, HumanEval, SWE-bench, MMLU, and 15+ standardized evaluations. Capabilities and context serve as tiebreakers (10%). Only models with the capabilities Warp needs are included in the tool-specific rankings.
We currently track 378 AI models compatible with Warp. This includes models from OpenAI, Anthropic, Google, DeepSeek, and other providers accessible via API.
Many open-source models are compatible with Warp through API providers like OpenRouter, Together AI, and Groq. Check our rankings to see which open-source models perform best.
Rankings refresh whenever the underlying benchmark, pricing, and catalog sources refresh. That means some signals update faster than others, and the page reflects the latest verified source data available.