Prix temps réel depuis OpenRouter + Benchmarks agentic
| Modèle | SWE-Ver | SWE Pro | MCP | Term | Fin | Coding | Notes |
|---|---|---|---|---|---|---|---|
OpenAI GPT-5.5 | 82.6% | 58.6% | — | 82.7% | — | 1520 |
Terminal-Bench 82.7%, Expert-SWE 73.1% |
Claude Opus 4.7 | 87.6% | 64.3% | 77.3% | — | 64.4% | 1548 |
#1 SWE-Pro 64.3%, MCP-Atlas 77.3%, GPQA 94.2% |
Claude Sonnet 4.6 | 79.6% | 53.4% | 75.8% | — | 60.1% | 1530 |
79.6% SWE-Ver at ~50% Opus price. Arena 1530 |
DeepSeek V4 Pro | ~66% | — | — | — | — | — | ~66% SWE-Ver at 10x cheaper than frontier |
Qwen 3.6 Plus | — | — | — | — | — | — | No public agentic scores yet |
Kimi K2.6 | ~70% | — | — | — | — | — | ~70% SWE-Ver. 100 sub-agents, 1500 parallel calls |
MiniMax M2.7 | ~72.5% | — | — | — | — | — | ~72.5% SWE-Ver. Best overall value |
GLM-5.1 | — | 58.4% | — | — | — | — | SWE-Pro 58.4% best among non-OpenAI/Anthropic |
Grok 4.3 | — | — | — | — | — | — | No public agentic benchmark scores yet |
| Modèle | SWE Pro | SWE Ver | Coût Min /1M | Coût Max /1M | Coût Moyen /M | Budget 15$ (M messages) | Msgs/mois | ||
|---|---|---|---|---|---|---|---|---|---|
| ⏳ Chargement des prix... | |||||||||
#1 SWE-bench Pro (64.3%), meilleur tool invocation (77.3%). Choix premium.
79.6% SWE-Verified à ~50% prix d'Opus. Idéal quotidien.
~72.5% SWE-Ver prix imbattable. Coding autonome.
~66% SWE-Ver prix plancher. 1.6T MoE.
Terminal-Bench 82.7% (meilleur). Shell, debug.
| Modèle | /100K | Combined /1M | Usage |
|---|
Stratégie :
• Default : Sonnet 4.6
• Complexe : Opus 4.7
• Fallback : GPT-5.5
• Budget : MiniMax/DeepSeek