INCLUDE: leaderboard
INCLUDE multilingual evaluation reported in Anthropic's Claude Opus 4.8 system card.
Metric: Score (system card). Source: anthropic.com. Source: benchmarklist.com. Saturation forecast: Around September 2027. 16 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Gemini 3.1 Pro (Preview) | 90.7 | #58 |
| 2 | Claude Mythos 5 | 90.5 | #2 |
| 3 | Claude Mythos Preview | 90.1 | #4 |
| 4 | Claude Opus 5 | 89.8 | #12 |
| 5 | Claude Opus 4.8 | 88.5 | #37 |
| 6 | GPT-5.4 | 88.3 | #79 |
| 7 | Claude Opus 4.6 (Max) | 87.4 | #63 (Claude Opus 4.6) |
| 8 | Claude Opus 4.7 | 87 | #49 |
| 9 | Claude Sonnet 5 | 86.5 | #57 |
| 10 | Qwen 3.7 Max | 86.2 | #75 |
| 11 | DeepSeek V4 Pro (Max) | 86.1 | #102 (DeepSeek V4 Pro) |
| 12 | Claude Sonnet 4.6 | 85.7 | #90 |
| 13 | Qwen 3.6 Plus | 85.1 | #120 |
| 14 | GLM-5.1 (Thinking) | 84.3 | #97 (GLM-5.1) |
| 15 | Kimi K2.6 (Thinking) | 84.2 | #104 (Kimi K2.6) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=include · How It Works · Data refreshed daily, snapshot 2026-10-20.