Live standings for 72 frontier models and 12 agent frameworks — capability measured on the kind of work you're actually doing, priced against what it costs per million tokens. Every number links to its public source, and anything we can't source is left blank instead of estimated.
Auto-refreshed daily · last update 2026-10-12 05:58 UTC
The picks below come from measured human-preference scores on each kind of work, divided against live API pricing. Change the task or set a budget →
| Model | Provider | Released | Context | Input /1M | Output /1M |
|---|---|---|---|---|---|
| Claude Haiku 5.5 | Anthropic | 2026-10-07 new | 1M | $0.10 | $0.50 |
| Nano Banana 2.1 | 2026-10-06 new | 66K | $1.50 | $7.50 | |
| Mistral Large 4 | Mistral | 2026-10-06 new | 1.048576M | $0.68 | $2.09 |
| GPT-6.1 Sol Pro | OpenAI | 2026-09-29 new | 1.05M | $2.00 | $10.00 |
| GPT-6.1 Sol | OpenAI | 2026-09-29 new | 1.05M | $2.00 | $10.00 |
| Claude Sonnet 5.5 | Anthropic | 2026-09-28 new | 1M | $2.00 | $10.00 |
| GLM 5.3 Prime | Z.ai (Zhipu) | 2026-09-23 new | 1M | $2.80 | $8.80 |
| Qwen3.8 Max Prime | Qwen (Alibaba) | 2026-09-23 new | 1M | $4.00 | $12.00 |
| Claude Opus 5.5 | Anthropic | 2026-09-22 new | 1M | $4.00 | $20.00 |
| GPT-6 Luna Pro | OpenAI | 2026-09-22 new | 1.05M | $0.10 | $0.50 |
| GPT-6 Luna | OpenAI | 2026-09-22 new | 1.05M | $0.10 | $0.50 |
| GPT-6 Sol Pro | OpenAI | 2026-09-22 new | 1.05M | $2.00 | $10.00 |
| GPT-6 Sol | OpenAI | 2026-09-22 new | 1.05M | $2.00 | $10.00 |
| Command A+ | Cohere | 2026-09-22 new | 192K | $0.30 | $1.50 |
| Qwen3.8 Omni Flash | Qwen (Alibaba) | 2026-09-21 new | 1M | $0.15 | $0.47 |
| Grok 4.7 | xAI | 2026-09-21 new | 500K | $2.00 | $6.00 |
Source: OpenRouter model catalog · retrieved 2026-10-12
General and Coding are Arena Elo for that category — human preference votes, higher is better. AA is the Artificial Analysis Intelligence Index, a benchmark-based composite on a different scale; it's shown beside the Elo columns as an independent cross-check, never blended with them. Blank means no published score, never an estimate. Price is blended (input×3 + output×1) ÷ 4 per million tokens; 19 models tagged varies are priced differently by UTC day or hour, and the full schedule is in the API. Click any header to sort.
| Model | Provider | General | Coding | AA | $/1M | Context | Tools | Released |
|---|---|---|---|---|---|---|---|---|
Claude Haiku 5.5anthropic/claude-haiku-5.5 |
Anthropic | — | — | 43.4 | $0.20 varies | 1M | tools | 2026-10-07 |
Nano Banana 2.1google/gemini-nano-banana-2.1 |
— | — | — | $3.00 | 66K | tools | 2026-10-06 | |
Mistral Large 4mistralai/mistral-large-4-0 |
Mistral | — | — | — | $1.03 | 1.048576M | tools | 2026-10-06 |
GPT-6.1 Sol Proopenai/gpt-6.1-sol-pro |
OpenAI | — | — | — | $4.00 varies | 1.05M | tools | 2026-09-29 |
GPT-6.1 Solopenai/gpt-6.1-sol |
OpenAI | 1447 | 1487 | 51.8 | $4.00 varies | 1.05M | tools | 2026-09-29 |
Claude Sonnet 5.5anthropic/claude-sonnet-5.5 |
Anthropic | 1471 | 1513 | 56 | $4.00 | 1M | tools | 2026-09-28 |
GLM 5.3 Primez-ai/glm-5.3-prime |
Z.ai (Zhipu) | — | — | — | $4.30 | 1M | tools | 2026-09-23 |
Qwen3.8 Max Primeqwen/qwen3.8-max-prime |
Qwen (Alibaba) | — | — | — | $6.00 | 1M | tools | 2026-09-23 |
Claude Opus 5.5anthropic/claude-opus-5.5 |
Anthropic | 1515 | 1547 | 57.6 | $8.00 | 1M | tools | 2026-09-22 |
GPT-6 Luna Proopenai/gpt-6-luna-pro |
OpenAI | — | — | — | $0.20 varies | 1.05M | tools | 2026-09-22 |
GPT-6 Lunaopenai/gpt-6-luna |
OpenAI | 1391 | 1439 | 38.1 | $0.20 varies | 1.05M | tools | 2026-09-22 |
GPT-6 Sol Proopenai/gpt-6-sol-pro |
OpenAI | — | — | — | $4.00 varies | 1.05M | tools | 2026-09-22 |
GPT-6 Solopenai/gpt-6-sol |
OpenAI | 1395 | 1447 | 47.6 | $4.00 varies | 1.05M | tools | 2026-09-22 |
Command A+cohere/command-a-plus |
Cohere | — | — | — | $0.60 | 192K | tools | 2026-09-22 |
Qwen3.8 Omni Flashqwen/qwen3.8-omni-flash |
Qwen (Alibaba) | — | — | — | $0.23 | 1M | tools | 2026-09-21 |
Grok 4.7x-ai/grok-4.7 |
xAI | 1399 | 1427 | 46.4 | $3.00 varies | 500K | tools | 2026-09-21 |
GLM 5.3 FlashXz-ai/glm-5.3-flashx |
Z.ai (Zhipu) | — | — | — | $0.59 | 1.048576M | tools | 2026-09-18 |
DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash |
DeepSeek | 1462 | 1506 | 39.5 | $0.53 | 1.048576M | tools | 2026-09-10 |
GPT-6 Astraopenai/gpt-6-astra |
OpenAI | 1440 | 1487 | 52.7 | $20.00 varies | 1.05M | tools | 2026-09-04 |
GPT-6 Astra Proopenai/gpt-6-astra-pro |
OpenAI | — | — | — | $20.00 varies | 1.05M | tools | 2026-09-04 |
Qwen3.8 Max (0902)qwen/qwen3.8-max-0902 |
Qwen (Alibaba) | 1483 | 1502 | 45.4 | $3.00 | 1M | tools | 2026-09-03 |
Gemini 3.8 Flashgoogle/gemini-3.8-flash |
1499 | 1510 | 40.9 | $1.50 | 1.048576M | tools | 2026-09-02 | |
Claude Fable 5.1anthropic/claude-fable-5.1 |
Anthropic | 1510 | 1528 | 53.4 | $20.00 | 1M | tools | 2026-09-01 |
GLM 5.3 Flashz-ai/glm-5.3-flash |
Z.ai (Zhipu) | 1471 | 1508 | 41.8 | $0.24 | 1.048576M | tools | 2026-08-26 |
Qwen3.8 Flashqwen/qwen3.8-flash |
Qwen (Alibaba) | — | — | — | $0.23 | 1M | tools | 2026-08-26 |
DeepSeek V4 Flash Vision Expdeepseek/deepseek-v4-flash-vision-exp |
DeepSeek | — | — | 34.8 | $0.33 | 1.048576M | tools | 2026-08-21 |
GLM 5.3z-ai/glm-5.3 |
Z.ai (Zhipu) | 1471 | 1496 | 44.8 | $1.26 | 1.048576M | tools | 2026-08-18 |
Qwen3.8 27Bqwen/qwen3.8-27b |
Qwen (Alibaba) | 1441 | 1482 | 33.7 | $0.60 | 1M | tools | 2026-08-14 |
Gemini 3.7 Flashgoogle/gemini-3.7-flash |
1486 | 1497 | 39.6 | $1.50 | 1.048576M | tools | 2026-08-13 | |
Qwen3.8 2.4T A95Bqwen/qwen3.8-2.4t-a95b |
Qwen (Alibaba) | — | — | 39.9 | $3.00 | 1.048576M | tools | 2026-08-12 |
Grok 4.6x-ai/grok-4.6 |
xAI | 1428 | 1465 | 44.3 | $3.00 varies | 500K | tools | 2026-08-12 |
DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-0813 |
DeepSeek | 1451 | 1469 | 36 | $0.99 varies | 1.048576M | tools | 2026-08-12 |
DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731 |
DeepSeek | 1432 | 1457 | 34.3 | $0.17 | 1.048576M | tools | 2026-07-31 |
Qwen3.7 Flashqwen/qwen3.7-flash |
Qwen (Alibaba) | — | — | — | $0.06 varies | 1M | tools | 2026-07-27 |
Claude Opus 5anthropic/claude-opus-5 |
Anthropic | 1507 | 1534 | 50.8 | $10.00 | 1M | tools | 2026-07-24 |
Gemini 3.6 Flashgoogle/gemini-3.6-flash |
1479 | 1491 | 34 | $1.50 | 1.048576M | tools | 2026-07-21 | |
Gemini 3.5 Flash Litegoogle/gemini-3.5-flash-lite |
1435 | 1453 | 22.2 | $0.85 | 1.048576M | tools | 2026-07-21 | |
Kimi K3moonshotai/kimi-k3 |
Moonshot AI | 1476 | 1508 | 43.6 | $3.05 | 1.048576M | tools | 2026-07-16 |
Grok 4.5x-ai/grok-4.5 |
xAI | 1448 | 1474 | 38.8 | $3.00 varies | 500K | tools | 2026-07-08 |
Claude Sonnet 5anthropic/claude-sonnet-5 |
Anthropic | 1442 | 1483 | 38.2 | $4.00 | 1M | tools | 2026-06-30 |
Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)google/gemini-3.1-flash-lite-image |
— | — | — | $0.56 | 66K | — | 2026-06-30 | |
Nano Banana 2 (Gemini 3.1 Flash Image)google/gemini-3.1-flash-image |
— | — | — | $1.13 | 131K | — | 2026-06-18 | |
Nano Banana Pro (Gemini 3 Pro Image)google/gemini-3-pro-image |
— | — | — | $4.50 | 131K | tools | 2026-06-18 | |
GLM 5.2z-ai/glm-5.2 |
Z.ai (Zhipu) | 1470 | 1485 | 33.7 | $1.79 | 1.048576M | tools | 2026-06-16 |
Kimi K2.7 Codemoonshotai/kimi-k2.7-code |
Moonshot AI | — | — | 25.8 | $1.34 | 262K | tools | 2026-06-12 |
Claude Fable 5anthropic/claude-fable-5 |
Anthropic | 1491 | 1519 | 49.6 | $20.00 | 1M | tools | 2026-06-09 |
Qwen3.7 Plusqwen/qwen3.7-plus |
Qwen (Alibaba) | 1455 | 1473 | 25.2 | $0.56 varies | 1M | tools | 2026-06-03 |
MiniMax M3minimax/minimax-m3 |
MiniMax | 1433 | 1469 | 29.2 | $0.53 | 1.048576M | tools | 2026-05-31 |
Claude Opus 4.8anthropic/claude-opus-4.8 |
Anthropic | 1454 | 1487 | 41.8 | $10.00 | 1M | tools | 2026-05-27 |
Grok Build 0.1x-ai/grok-build-0.1 |
xAI | — | — | 27.2 | $1.25 varies | 256K | tools | 2026-05-20 |
Mistral Medium 3.5mistralai/mistral-medium-3-5 |
Mistral | 1421 | 1461 | 14.2 | $3.00 | 262K | tools | 2026-04-30 |
Grok 4.3x-ai/grok-4.3 |
xAI | 1397 | 1415 | 24.9 | $1.56 varies | 1M | tools | 2026-04-30 |
DeepSeek V4 Pro 0423deepseek/deepseek-v4-pro |
DeepSeek | 1451 | 1469 | 30.4 | $1.20 | 1.048576M | tools | 2026-04-24 |
DeepSeek V4 Flash 0423deepseek/deepseek-v4-flash |
DeepSeek | 1432 | 1457 | 24.4 | $0.33 | 1.048576M | tools | 2026-04-24 |
Kimi K2.6moonshotai/kimi-k2.6 |
Moonshot AI | 1455 | 1488 | 27 | $1.34 | 262K | tools | 2026-04-20 |
GLM 5.1z-ai/glm-5.1 |
Z.ai (Zhipu) | 1461 | 1485 | 26.1 | $1.49 | 205K | tools | 2026-04-07 |
GLM 5V Turboz-ai/glm-5v-turbo |
Z.ai (Zhipu) | 1437 | 1466 | 23.5 | $1.90 | 203K | tools | 2026-04-01 |
Grok 4.20 Multi-Agentx-ai/grok-4.20-multi-agent |
xAI | — | — | — | $1.56 varies | 2M | — | 2026-03-31 |
Grok 4.20x-ai/grok-4.20 |
xAI | — | — | 25.7 | $1.56 varies | 2M | tools | 2026-03-31 |
MiniMax M2.7minimax/minimax-m2.7 |
MiniMax | 1405 | 1454 | 22.8 | $0.37 | 205K | tools | 2026-03-18 |
Mistral Small 4mistralai/mistral-small-2603 |
Mistral | — | — | 11.3 | $0.26 | 262K | tools | 2026-03-16 |
GLM 5 Turboz-ai/glm-5-turbo |
Z.ai (Zhipu) | — | — | 26.6 | $1.90 | 203K | tools | 2026-03-15 |
MiniMax M2.5minimax/minimax-m2.5 |
MiniMax | 1359 | 1381 | 22.8 | $0.47 | 205K | tools | 2026-02-12 |
Kimi K2.5moonshotai/kimi-k2.5 |
Moonshot AI | 1445 | 1483 | 23.5 | $1.00 | 262K | tools | 2026-01-27 |
MiniMax M2-herminimax/minimax-m2-her |
MiniMax | — | — | — | $0.53 | 66K | — | 2026-01-23 |
MiniMax M2.1minimax/minimax-m2.1 |
MiniMax | 1392 | 1421 | 20.9 | $0.53 | 205K | tools | 2025-12-23 |
Devstral 2 2512mistralai/devstral-2512 |
Mistral | — | — | 8.6 | $0.80 | 262K | tools | 2025-12-09 |
Ministral 3 14B 2512mistralai/ministral-14b-2512 |
Mistral | — | — | 6 | $0.20 | 262K | tools | 2025-12-02 |
Ministral 3 8B 2512mistralai/ministral-8b-2512 |
Mistral | — | — | 5.5 | $0.15 | 262K | tools | 2025-12-02 |
Ministral 3 3B 2512mistralai/ministral-3b-2512 |
Mistral | — | — | 4.8 | $0.10 | 131K | tools | 2025-12-02 |
Mistral Large 3 2512mistralai/mistral-large-2512 |
Mistral | — | — | 9.3 | $0.75 | 262K | tools | 2025-12-01 |
DeepSeek V3.2deepseek/deepseek-v3.2 |
DeepSeek | 1425 | 1449 | 21.5 | $0.40 | 164K | tools | 2025-12-01 |
Pricing: OpenRouter model catalog, retrieved 2026-10-12. Elo capability: Arena leaderboard dataset (CC-BY-4.0), retrieved 2026-10-12. AA index: Artificial Analysis, republished in the OpenRouter catalog.
Percentage of 500 real GitHub issues resolved. Entries are agent scaffold + model combinations, not bare models — the same model can move many points depending on the harness around it.
| # | Agent + model | Resolved | Date | Status |
|---|---|---|---|---|
| 1 | Sonar Foundation Agent + Claude 4.5 Opus | 79.2% | 2025-12-05 | self-reported |
| 2 | live-SWE-agent + Claude 4.5 Opus medium (20251101) | 79.2% | 2025-12-15 | self-reported |
| 3 | TRAE + Doubao-Seed-Code | 78.8% | 2025-09-28 | self-reported |
| 4 | live-SWE-agent + Gemini 3 Pro Preview (2025-11-18) | 77.4% | 2025-11-20 | self-reported |
| 5 | EPAM AI/Run Developer Agent v20250719 + Claude 4 Sonnet | 76.8% | 2025-08-04 | self-reported |
| 6 | Atlassian Rovo Dev (2025-09-02) | 76.8% | 2025-09-02 | self-reported |
| 7 | Claude 4.5 Opus (high) | 76.8% | 2026-02-17 | self-reported |
| 8 | ACoder | 76.4% | 2025-08-19 | self-reported |
| 9 | Gemini 3 Flash (high) | 75.8% | 2026-02-17 | self-reported |
| 10 | MiniMax M2.5 (high) | 75.8% | 2026-02-17 | self-reported |
Source: SWE-bench leaderboard · fetched 2026-10-12, board last updated 2026-02-26 · full top 20 + framework standings →
A small, safe, replayable self-hosted agent — single static Go binary, zero deps, hard 8K context budget, policy-gated exec, append-only event log · 0 stars on GitHub.
gcrab.com →See it in the standingsGET /api/v1/route/coding.json returns the ranked capability-vs-cost table for that task. Also /llms.txt, /leaderboard.md, and the full API index. See API & Bots.