Quantitative and symbolic problem solving. Ranked by Arena text / math, priced against live API rates. 45 models have a published score on this board.
Capability published 2026-10-22 · pricing retrieved 2026-10-25
google/gemini-4-argongoogle/gemini-3.7-flashdeepseek/deepseek-v4-flash-0731google/gemini-3.7-flashRows marked frontier are Pareto-optimal — nothing we track is both stronger and cheaper. "Strength" rescales the board so 100% = parity with the leader.
| # | Model | Provider | Score | Strength | $/1M | Context | Tools |
|---|---|---|---|---|---|---|---|
| 1 | Gemini 4 Argongoogle/gemini-4-argon | 1538 | 100% | $4.00 | 1.048576M | tools | |
| 2 | Claude Opus 5anthropic/claude-opus-5 | Anthropic | 1533 | 99% | $10.00 | 1M | tools |
| 3 | Claude Fable 5.1anthropic/claude-fable-5.1 | Anthropic | 1532 | 98% | $20.00 | 1M | tools |
| 4 | Gemini 3.8 Flashgoogle/gemini-3.8-flash | 1532 | 98% | $1.66 | 1.048576M | tools | |
| 5 | Claude Opus 5.5anthropic/claude-opus-5.5 | Anthropic | 1518 | 94% | $8.00 | 1M | tools |
| 6 | Claude Fable 5anthropic/claude-fable-5 | Anthropic | 1516 | 94% | $20.00 | 1M | tools |
| 7 | Gemini 3.7 Flashgoogle/gemini-3.7-flash | 1510 | 92% | $1.50 | 1.048576M | tools | |
| 8 | Gemini 3.6 Flashgoogle/gemini-3.6-flash | 1507 | 91% | $1.50 | 1.048576M | tools | |
| 9 | GLM 5.3 Flashz-ai/glm-5.3-flash | Z.ai (Zhipu) | 1502 | 90% | $0.24 | 1.048576M | tools |
| 10 | Qwen3.8 Max (0902)qwen/qwen3.8-max-0902 | Qwen (Alibaba) | 1501 | 89% | $3.00 | 1M | tools |
| 11 | Claude Sonnet 5.5anthropic/claude-sonnet-5.5 | Anthropic | 1498 | 89% | $4.00 | 1M | tools |
| 12 | GLM 5.3z-ai/glm-5.3 | Z.ai (Zhipu) | 1498 | 88% | $0.41 | 1.048576M | tools |
| 13 | Kimi K3moonshotai/kimi-k3 | Moonshot AI | 1493 | 87% | $2.88 | 1.048576M | tools |
| 14 | GPT-6.1 Solopenai/gpt-6.1-sol | OpenAI | 1490 | 86% | $4.00 | 1.05M | tools |
| 15 | Claude Opus 4.8anthropic/claude-opus-4.8 | Anthropic | 1486 | 85% | $10.00 | 1M | tools |
| 16 | GLM 5.2z-ai/glm-5.2 | Z.ai (Zhipu) | 1484 | 85% | $1.77 | 1.048576M | tools |
| 17 | DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash | DeepSeek | 1479 | 83% | $0.27 | 1.048576M | tools |
| 18 | Kimi K2.6moonshotai/kimi-k2.6 | Moonshot AI | 1474 | 82% | $1.34 | 262K | tools |
| 19 | GLM 5.1z-ai/glm-5.1 | Z.ai (Zhipu) | 1474 | 82% | $2.15 | 205K | tools |
| 20 | Kimi K2.5moonshotai/kimi-k2.5 | Moonshot AI | 1470 | 81% | $1.00 | 262K | tools |
| 21 | Claude Sonnet 5anthropic/claude-sonnet-5 | Anthropic | 1467 | 80% | $4.00 | 1M | tools |
| 22 | Qwen3.7 Plusqwen/qwen3.7-plus | Qwen (Alibaba) | 1467 | 80% | $0.56 | 1M | tools |
| 23 | GPT-6 Astraopenai/gpt-6-astra | OpenAI | 1466 | 80% | $20.00 | 1.05M | tools |
| 24 | Grok 4.5x-ai/grok-4.5 | xAI | 1460 | 78% | $3.00 | 500K | tools |
| 25 | Qwen3.8 27Bqwen/qwen3.8-27b | Qwen (Alibaba) | 1455 | 77% | $0.78 | 1M | tools |
Capability: Arena leaderboard dataset (CC-BY-4.0), Arena text / math, published 2026-10-22. Pricing: OpenRouter, retrieved 2026-10-25. (input x 3 + output x 1) / 4.
curl -s https://agentleaderboards.com/api/v1/route/math.json | jq .picksNo key, open CORS, refreshed daily. Set your own budget and constraints →
Writing & editing code · Autonomous agent work · Tool-call reliability · Following operator instructions · Recovering from shell errors · Hard reasoning · Precise instruction following · Long multi-turn chat · Long inputs · Creative writing · General assistant · Software & IT services · Legal & government · Medicine & healthcare · Science · Business & finance · Writing & language