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.
Arena code
Top 10 of 20Full board| # | Model | Score |
|---|---|---|
| 1 | OpenAI: GPT-6 AstraOpenAI · gpt-6-astra · max effort | 1796 |
| 2 | Anthropic: Claude Fable 5.1Anthropic · claude-fable-5.1 · max effort | 1764 |
| 3 | Anthropic: Claude Opus 5Anthropic · claude-opus-5 · max effort | 1688 |
| 4 | Qwen3.8 Max 0902Alibaba · qwen3.8-max-0902 | 1685 |
| 5 | Moonshot: Kimi K3Moonshot · kimi-k3 · max effort | 1674 |
| 6 | Qwen3.8 MaxAlibaba · qwen3.8 · max effort | 1670 |
| 7 | Anthropic: Claude Opus 5Anthropic · claude-opus-5 · high effort | 1661 |
| 8 | Meta: Muse Spark 1.3Meta · muse-spark-1.3 · max effort | 1650 |
| 9 | Alibaba: Qwen 3.8 Flash NextAlibaba · qwen3.8-flash-next | 1631 |
| 10 | Anthropic: Claude Fable 5Anthropic · claude-fable-5 | 1628 |
Arena agent
10 modelsFull board| # | Model | Score |
|---|---|---|
| 1 | Anthropic: Claude Fable 5.1Anthropic · claude-fable-5.1 · max effort | 14.51 |
| 2 | OpenAI: GPT-6 AstraOpenAI · gpt-6-astra · max effort | 12.55 |
| 3 | Anthropic: Claude Opus 5Anthropic · claude-opus-5 · high effort | 11.42 |
| 4 | Anthropic: Claude Opus 5Anthropic · claude-opus-5 · max effort | 10.79 |
| 5 | Anthropic: Claude Fable 5Anthropic · Claude Fable 5 · high effort | 9.15 |
| 6 | OpenAI: GPT-5.6 SolOpenAI · gpt-5.6-sol · xhigh effort | 7.75 |
| 7 | Anthropic: Claude Opus 4.8 ThinkingAnthropic · claude-opus-4-8 · high effort | 7.69 |
| 8 | Moonshot: Kimi K3Moonshot · kimi-k3 · max effort | 6.59 |
| 9 | Anthropic: Claude Sonnet 5 ThinkingAnthropic · Claude Sonnet 5 · high effort | 6.31 |
| 10 | Hy4 previewTencent · hy4-preview | 5.37 |
Arena text
Top 10 of 19Full board| # | Model | Score |
|---|---|---|
| 1 | Anthropic: Claude Fable 5Anthropic · claude-fable-5 | 1507 |
| 2 | Anthropic: Claude 4.6 Opus ThinkingAnthropic · claude-opus-4-6 · high effort | 1505 |
| 3 | Anthropic: Claude Fable 5.1Anthropic · claude-fable-5.1 · max effort | 1504 |
| 4 | Anthropic: Claude 4.7 Opus ThinkingAnthropic · claude-opus-4-7 · high effort | 1502 |
| 5 | Meta: Muse Spark 1.2Meta · muse-spark-1.2 · xhigh effort | 1499 |
| 6 | Anthropic: Claude 4.6 Opus ThinkingAnthropic · claude-opus-4.6 | 1498 |
| 7 | Anthropic: Claude 4.7 Opus ThinkingAnthropic · claude-opus-4-7 | 1494 |
| 8 | Google: Gemini 3.8 FlashGoogle · gemini-3.8-flash · high effort | 1494 |
| 9 | Anthropic: Claude Opus 5Anthropic · claude-opus-5 · high effort | 1493 |
| 10 | Meta: Muse Spark 1.1Meta · muse-spark-1.1 | 1492 |
Arena vision
Top 10 of 19Full board| # | Model | Score |
|---|---|---|
| 1 | Anthropic: Claude Fable 5Anthropic · claude-fable-5 | 1313 |
| 2 | Anthropic: Claude 4.7 Opus ThinkingAnthropic · claude-opus-4-7 · high effort | 1301 |
| 3 | Qwen3.8 MaxAlibaba · qwen3.8 · max effort | 1300 |
| 4 | Anthropic: Claude 4.6 Opus ThinkingAnthropic · claude-opus-4-6 · high effort | 1299 |
| 5 | Anthropic: Claude 4.7 Opus ThinkingAnthropic · claude-opus-4-7 | 1299 |
| 6 | Anthropic: Claude 4.6 Opus ThinkingAnthropic · claude-opus-4.6 | 1293 |
| 7 | Meta: Muse Spark 1.2Meta · muse-spark-1.2 · xhigh effort | 1292 |
| 8 | Anthropic: Claude Opus 5Anthropic · claude-opus-5 · high effort | 1290 |
| 9 | Google: Gemini 3 ProGoogle · gemini-3-pro | 1289 |
| 10 | OpenAI: GPT-5.5OpenAI · gpt-5.5 | 1286 |
Artificial Analysis
Top 10 of 129Full board| # | Model | Score |
|---|---|---|
| 1 | OpenAI: GPT-6 AstraOpenAI · gpt-6-astra | 61AA intelligence |
| 2 | xAI: Grok 4.6xAI · grok-4.6 · high effort | 61AA intelligence |
| 3 | Meta: Muse Spark 1.3Meta · muse-spark-1.3 · xhigh effort | 61AA intelligence |
| 4 | Anthropic: Claude Fable 5.1Anthropic · claude-fable-5.1 | 53.4AA intelligence |
| 5 | Anthropic: Claude Opus 5Anthropic · claude-opus-5 | 50.7AA intelligence |
| 6 | Anthropic: Claude Fable 5Anthropic · claude-fable-5 | 49.7AA intelligence |
| 7 | OpenAI: GPT-5.6 SolOpenAI · gpt-5.6-sol | 47.1AA intelligence |
| 8 | Z.ai: GLM-5.3z-ai · glm-5.3 | 44.9AA intelligence |
| 9 | xAI: Grok 4.6x-ai · grok-4.6 | 44.4AA intelligence |
| 10 | Moonshot: Kimi K3moonshotai · kimi-k3 | 43.8AA intelligence |
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.