Model catalog
Benchmarks
Arena Elo from free open daily snapshots on GitHub (text, code, vision, agent), plus a sparse Artificial Analysis subset OpenRouter embeds. One score set is cross-linked onto provider clones of the same model. Arena may score the same base model at different reasoning efforts, so those rows stay separate and link to the base model only when it exists in the catalog. The open dumps publish 20 models per Arena board (10 on agent), so a full board is short by design. Empty on a single board is a gap, not a ranking of zero.
| # | Model | Score |
|---|---|---|
| 1 | OpenAI: GPT-6 AstraOpenAI · gpt-6-astra · max effort | 1800Arena code |
| 2 | Anthropic: Claude Fable 5.1Anthropic · claude-fable-5.1 · max effort | 1758Arena code |
| 3 | Anthropic: Claude Opus 5Anthropic · claude-opus-5 · max effort | 1687Arena code |
| 4 | Qwen3.8 Max 0902Alibaba · qwen3.8-max-0902 | 1681Arena code |
| 5 | Moonshot: Kimi K3Moonshot · kimi-k3 · max effort | 1674Arena code |
| 6 | Qwen3.8 MaxAlibaba · qwen3.8 · max effort | 1671Arena code |
| 7 | Anthropic: Claude Opus 5Anthropic · claude-opus-5 · high effort | 1660Arena code |
| 8 | Meta: Muse Spark 1.3Meta · muse-spark-1.3 · max effort | 1652Arena code |
| 9 | Qwen3.8 Flash NextAlibaba · qwen3.8-flash-next | 1635Arena code |
| 10 | Anthropic: Claude Fable 5Anthropic · claude-fable-5 · high effort | 1628Arena code |
| 11 | Hy4 previewTencent · hy4-preview | 1624Arena code |
| 12 | Meta: Muse Spark 1.3Meta · muse-spark-1.3 · xhigh effort | 1623Arena code |
| 13 | xAI: Grok 4.6xAI · grok-4.6 · high effort | 1618Arena code |
| 14 | OpenAI: GPT-5.6 SolOpenAI · gpt-5.6-sol-xhigh · codex-harness effort | 1617Arena code |
| 15 | DeepSeek: V4.1 FlashDeepSeek · deepseek-v4.1-flash · max effort | 1614Arena code |
| 16 | Mistral: GLM-5.3Z.ai · glm-5.3 · max effort | 1614Arena code |
| 17 | Z.ai: GLM 5.3 FlashZ.ai · glm-5.3-flash | 1607Arena code |
| 18 | Qwen3.8 27BAlibaba · qwen3.8-27b | 1593Arena code |
| 19 | Mistral: GLM-5.2Z.ai · glm-5.2 · max effort | 1592Arena code |
| 20 | Google: Gemini 3.7 FlashGoogle · gemini-3.7-flash · high effort | 1587Arena code |
| 21 | deepseek-v4-pro-high-20260813DeepSeek · deepseek-v4-pro-high-20260813 · not linked in catalog | 1581Arena code |
| 22 | DeepSeek: V4 FlashDeepSeek · deepseek-v4-flash · high effort | 1580Arena code |
| 23 | Google: Gemini 3.8 FlashGoogle · gemini-3.8-flash · high effort | 1568Arena code |
| 24 | Anthropic: Claude Opus 4.8 ThinkingAnthropic · claude-opus-4-8 · high effort | 1559Arena code |
| 25 | Anthropic: Claude 4.7 Opus ThinkingAnthropic · claude-opus-4-7 | 1557Arena code |
| 26 | Anthropic: Claude 4.7 Opus ThinkingAnthropic · claude-opus-4-7 · high effort | 1555Arena code |
| 27 | xAI: Grok 4.5xAI · grok-4.5 | 1555Arena code |
| 28 | Anthropic: Claude 4.6 Opus ThinkingAnthropic · claude-opus-4-6 · high effort | 1547Arena code |
| 29 | Meta: Muse Spark 1.1Meta · muse-spark-1.1 | 1542Arena code |
| 30 | Anthropic: Claude Opus 4.8 ThinkingAnthropic · claude-opus-4-8 | 1539Arena code |
| 31 | Anthropic: Claude 4.6 Opus ThinkingAnthropic · claude-opus-4.6 | 1537Arena code |
| 32 | Anthropic: Claude Sonnet 5 ThinkingAnthropic · claude-sonnet-5 · high effort | 1537Arena code |
| 33 | Google: Gemini 3.6 FlashGoogle · gemini-3.6-flash · high effort | 1537Arena code |
| 34 | Meta: Muse Spark 1.2Meta · muse-spark-1.2 · xhigh effort | 1534Arena code |
| 35 | Anthropic: Claude Sonnet 4.6 ThinkingAnthropic · claude-sonnet-4-6 | 1521Arena code |
| 36 | OpenAI: GPT-5.6 TerraOpenAI · gpt-5.6-terra-xhigh · codex-harness effort | 1521Arena code |
| 37 | OpenAI: GPT-5.6 LunaOpenAI · gpt-5.6-luna-xhigh · codex-harness effort | 1519Arena code |
| 38 | seed-2.1-pro-previewBytedance · seed-2.1-pro-preview · not linked in catalog | 1519Arena code |
| 39 | Qwen3.7 MaxAlibaba · qwen3.7-max-20260517 | 1517Arena code |
| 40 | Hy3 (Free)Tencent · hy3 | 1513Arena code |
| 41 | OpenAI: GPT-5.5OpenAI · gpt-5.5-xhigh · codex-harness effort | 1510Arena code |
| 42 | Moonshot: Kimi K2.6Moonshot · kimi-k2.6 | 1509Arena code |
| 43 | Z.ai: GLM-5.1Z.ai · glm-5.1 | 1508Arena code |
| 44 | Google: Gemini 3.5 FlashGoogle · gemini-3.5-flash · high effort | 1500Arena code |
Sources
Arena Elo from Arena AI, via open dumps by oolong-tea-2026. Artificial Analysis indices via OpenRouter (subset). Artificial Analysis for the indices themselves. Plus vendor-reported launch evals collected from announcements, analyst writeups, launch blogs, and community benchmarks. As of .
Turn benchmark scores into working sessions
Run agents in a local Git-enabled workspace, connect to another machine when needed, and track the sessions and tokens behind your work. See what your AI subscriptions covered.
Data and list-price estimates may contain mistakes. Not investment advice.