LLM Leaderboard
Source-checked Text Arena entries for selected models in our existing catalog.
Catalog reviewed 2026-11-22; scores read from the Text Arena board dated 2026-11-20. These are evaluation variants, not interchangeable scores for every configuration of a model. This selection omits newer and unverified entries; it is not a complete ranking of current models. The imported composite, Hugging Face and MMLU estimates are withheld. The former proprietary-benchmark and intelligence-ROI claims have been withdrawn because no supporting method, test set or run record was available for this review.
Loading interactive filters...
Source-checked entries (34)
| Model | Evaluation variant | Arena score | Source |
|---|---|---|---|
| Gemini 4 Carbon | Gemini 4 Carbon (High) | 1527 ± 10 | Text Arena, 2026-11-20 |
| Gemini 4 Neon | Gemini 4 Neon (High) | 1513 ± 9 | Text Arena, 2026-11-20 |
| Claude Opus 5.5 | Claude Opus 5.5 (High) | 1506 ± 6 | Text Arena, 2026-11-20 |
| Claude Fable 5 | Claude Fable 5 (High) | 1504 ± 4 | Text Arena, 2026-11-20 |
| Claude Fable 5.1 | Claude Fable 5.1 (Max) | 1503 ± 5 | Text Arena, 2026-11-20 |
| Claude Fable 5.2 | Claude Fable 5.2 (Max) | 1503 ± 9 | Text Arena, 2026-11-20 |
| Muse Spark 1.3 | Muse Spark 1.3 (Max) | 1498 ± 5 | Text Arena, 2026-11-20 |
| Gemini 3.8 Flash | Gemini 3.8 Flash (High) | 1497 ± 4 | Text Arena, 2026-11-20 |
| Claude 4.7 Opus | Claude Opus 4.7 | 1494 ± 4 | Text Arena, 2026-11-20 |
| Muse Spark 1.1 | Muse Spark 1.1 | 1491 ± 4 | Text Arena, 2026-11-20 |
| Claude Opus 5 | Claude Opus 5 (High) | 1490 ± 4 | Text Arena, 2026-11-20 |
| Gemini 4 Hydrogen | Gemini 4 Hydrogen (High) | 1490 ± 9 | Text Arena, 2026-11-20 |
| GPT-5.6 Sol | GPT-5.6 Sol (xHigh) | 1485 ± 4 | Text Arena, 2026-11-20 |
| GLM-5.3 | GLM-5.3 (Max) | 1482 ± 5 | Text Arena, 2026-11-20 |
| Kimi K3.1 Pro | Kimi K3.1 Pro (Max) | 1482 ± 8 | Text Arena, 2026-11-20 |
| DeepSeek V4.1 Flash | DeepSeek-V4.1-Flash-20260910 (Max) | 1475 ± 6 | Text Arena, 2026-11-20 |
| GLM-5.2 | GLM-5.2 (Max) | 1475 ± 4 | Text Arena, 2026-11-20 |
| GPT-6 Astra | GPT-6 Astra (Max) | 1475 ± 5 | Text Arena, 2026-11-20 |
| Claude Opus 4.8 | Claude Opus 4.8 | 1474 ± 4 | Text Arena, 2026-11-20 |
| GPT-6.1 Terra | GPT-6.1 Terra (Max) | 1474 ± 8 | Text Arena, 2026-11-20 |
| Claude Sonnet 5.5 | Claude Sonnet 5.5 (xHigh) | 1473 ± 6 | Text Arena, 2026-11-20 |
| GPT-5.6 Terra | GPT-5.6 Terra (xHigh) | 1468 ± 4 | Text Arena, 2026-11-20 |
| GPT-6.2 Astra | GPT-6.2 Astra (Max) | 1468 ± 12 | Text Arena, 2026-11-20 |
| Grok 4.5 | Grok 4.5 | 1466 ± 4 | Text Arena, 2026-11-20 |
| GPT-6.2 Sol | GPT-6.2 Sol (Max) | 1465 ± 12 | Text Arena, 2026-11-20 |
| DeepSeek-V4 Pro | DeepSeek-V4-Pro (High, 20260813) | 1464 ± 7 | Text Arena, 2026-11-20 |
| Claude Sonnet 5 | Claude Sonnet 5 (High) | 1461 ± 4 | Text Arena, 2026-11-20 |
| Grok 4.6 | Grok 4.6 (High) | 1457 ± 5 | Text Arena, 2026-11-20 |
| GPT-5.6 Luna | GPT-5.6 Luna (xHigh) | 1453 ± 4 | Text Arena, 2026-11-20 |
| GPT-6 Luna | GPT-6 Luna (Max) | 1443 ± 4 | Text Arena, 2026-11-20 |
| Grok 4.7 | Grok 4.7 (xHigh) | 1443 ± 5 | Text Arena, 2026-11-20 |
| Mistral Large 4 | Mistral Large 4 | 1423 ± 7 | Text Arena, 2026-11-20 |
| Claude Haiku 5.5 | Claude Haiku 5.5 (High) | 1421 ± 6 | Text Arena, 2026-11-20 |
| Mistral Large 3 | Mistral Large 3 | 1415 ± 3 | Text Arena, 2026-11-20 |
What is measured
The linked Text Arena board reports preference scores for named evaluation entries. Its displayed uncertainty is retained. A higher score is not a guarantee of better coding, reasoning or task success in your workload.
What is withheld
A model without a verified entry receives no score or rank here. Missing evidence is not a zero, a tie or evidence that the model is worse.
How to compare
Keep model variant, evaluation date and benchmark conditions with each result. Validate cost and quality on your own workload before choosing a deployment.