Model catalog
Benchmarks
Public scores, so you can compare models next to their prices. 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 | Anthropic: Claude Opus 5.5Anthropic · claude-opus-5.5 · max effort | 1814 |
| 2 | OpenAI: GPT-6 AstraOpenAI · gpt-6-astra · max effort | 1788 |
| 3 | Anthropic: Claude Sonnet 5.5Anthropic · claude-sonnet-5.5 · xhigh effort | 1773 |
| 4 | OpenAI: GPT-6.1 SolOpenAI · gpt-6.1-sol · max effort | 1757 |
| 5 | Anthropic: Claude Fable 5.1Anthropic · claude-fable-5.1 · max effort | 1745 |
| 6 | Anthropic: Claude Sonnet 5.5Anthropic · claude-sonnet-5.5 · high effort | 1716 |
| 7 | Anthropic: Claude Opus 5Anthropic · claude-opus-5 · max effort | 1692 |
| 8 | OpenAI: GPT-6 SolOpenAI · gpt-6-sol · max effort | 1687 |
| 9 | Google: Gemini 4 ArgonGoogle · gemini-4-argon · high effort | 1678 |
| 10 | Qwen3.8 MaxAlibaba · qwen3.8 · max effort | 1672 |
Arena agent
10 modelsFull board| # | Model | Score |
|---|---|---|
| 1 | Anthropic: Claude Fable 5.1Anthropic · claude-fable-5.1 · max effort | 14.31 |
| 2 | Anthropic: Claude Opus 5.5Anthropic · claude-opus-5.5 · high effort | 13.82 |
| 3 | Anthropic: Claude Sonnet 5.5Anthropic · Claude Sonnet 5.5 · max effort | 12.52 |
| 4 | OpenAI: GPT-6 AstraOpenAI · gpt-6-astra · max effort | 12.27 |
| 5 | OpenAI: GPT-6.1 SolOpenAI · gpt-6.1-sol · max effort | 11.23 |
| 6 | OpenAI: GPT-6 SolOpenAI · gpt-6-sol · max effort | 9.71 |
| 7 | Anthropic: Claude Opus 5Anthropic · claude-opus-5 · high effort | 8.67 |
| 8 | Anthropic: Claude Fable 5Anthropic · claude-fable-5 · high effort | 8.21 |
| 9 | Anthropic: Claude Opus 5Anthropic · claude-opus-5 · max effort | 7.92 |
| 10 | Google: Gemini 4 ArgonGoogle · gemini-4-argon · high effort | 7.57 |
Arena text
Top 10 of 19Full board| # | Model | Score |
|---|---|---|
| 1 | Google: Gemini 4 ArgonGoogle · gemini-4-argon · high effort | 1525 |
| 2 | Anthropic: Claude 4.6 Opus ThinkingAnthropic · claude-opus-4-6 · high effort | 1505 |
| 3 | Anthropic: Claude Fable 5Anthropic · claude-fable-5 · high effort | 1504 |
| 4 | Anthropic: Claude Opus 5.5Anthropic · claude-opus-5.5 · high effort | 1504 |
| 5 | Anthropic: Claude Fable 5.1Anthropic · claude-fable-5.1 · max effort | 1501 |
| 6 | Anthropic: Claude Opus 4.7Anthropic · claude-opus-4-7 · high effort | 1501 |
| 7 | Anthropic: Claude 4.6 Opus ThinkingAnthropic · claude-opus-4.6 | 1497 |
| 8 | Google: Gemini 3.8 FlashGoogle · gemini-3.8-flash · high effort | 1495 |
| 9 | Anthropic: Claude Opus 4.7Anthropic · claude-opus-4-7 | 1494 |
| 10 | Meta: Muse Spark 1.2Meta · muse-spark-1.2 · xhigh effort | 1494 |
Arena vision
Top 10 of 19Full board| # | Model | Score |
|---|---|---|
| 1 | Anthropic: Claude Fable 5Anthropic · claude-fable-5 · high effort | 1309 |
| 2 | Qwen3.8 MaxAlibaba · qwen3.8 · max effort | 1301 |
| 3 | Anthropic: Claude 4.6 Opus ThinkingAnthropic · claude-opus-4-6 · high effort | 1299 |
| 4 | Anthropic: Claude Opus 4.7Anthropic · claude-opus-4-7 · high effort | 1298 |
| 5 | Anthropic: Claude Opus 4.7Anthropic · claude-opus-4-7 | 1298 |
| 6 | Google: Gemini 3.7 FlashGoogle · gemini-3.7-flash · high effort | 1296 |
| 7 | Anthropic: Claude 4.6 Opus ThinkingAnthropic · claude-opus-4.6 | 1294 |
| 8 | Meta: Muse Spark 1.2Meta · muse-spark-1.2 · xhigh effort | 1293 |
| 9 | OpenAI: GPT-6.1 SolOpenAI · gpt-6.1-sol · max effort | 1291 |
| 10 | Google: Gemini 3.8 FlashGoogle · gemini-3.8-flash · high effort | 1290 |
Artificial Analysis
Top 10 of 218Full 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 Opus 5.5Anthropic · claude-opus-5-5 | 57.6AA intelligence |
| 5 | Anthropic: Claude Sonnet 5.5Anthropic · claude-sonnet-5-5 | 56AA intelligence |
| 6 | Anthropic: Claude Fable 5.1Anthropic · claude-fable-5.1 | 53.4AA intelligence |
| 7 | Google: Gemini 4 ArgonGoogle · gemini-4-argon | 52.6AA intelligence |
| 8 | OpenAI: GPT-6.1 SolOpenAI · gpt-6.1-sol | 51.8AA intelligence |
| 9 | Anthropic: Claude Opus 5Anthropic · claude-opus-5 | 50.8AA intelligence |
| 10 | Anthropic: Claude Fable 5Anthropic · claude-fable-5 | 49.6AA 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.