MultiNRC: leaderboard
MultiNRC benchmarks LLMs on 1,000+ culturally grounded reasoning questions by native French, Spanish, and Chinese speakers across four reasoning categor...
Metric: Score. Source: labs.scale.com. Source: scale.com. Source: benchmarklist.com. 44 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | Muse Spark 1.1 | 65.59 | #52 |
| 2 | Gemini 3.1 Pro (Preview) | 64.74 | #58 |
| 3 | Muse Spark | 59.05 | #64 |
| 4 | Gemini 3 Pro (Preview) | 58.96 | #66 |
| 5 | GPT-5.4 (2026-03-05) (xHigh) | 58.29 | #59 (GPT-5.4 (2026-03-05)) |
| 6 | Claude Opus 4.6 (Adaptive Reasoning, Max Effort) | 57.06 | #63 (Claude Opus 4.6) |
| 7 | GPT-5 | 52.13 | #98 |
| 8 | GPT-5.1 (Thinking) | 49 | #135 (GPT-5.1) |
| 9 | Claude Opus 4.5 (20251101) (Thinking) | 48.63 | #74 (Claude Opus 4.5 (20251101)) |
| 10 | Claude Opus 4.6 (Non-reasoning) | 48.34 | #63 (Claude Opus 4.6) |
| 11 | O3 (2025-04-16) (High) | 45.5 | #121 (O3 (2025-04-16)) |
| 12 | Gemini 2.5 Pro (Preview 06-05) | 45.12 | #106 |
| 13 | O3 (2025-04-16) (Medium) | 44.45 | #121 (O3 (2025-04-16)) |
| 14 | GPT-5.2 | 42.18 | #110 |
| 15 | Claude Opus 4.5 (20251101) | 41.23 | #74 |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=multinrc · How It Works · Data refreshed daily, snapshot 2026-10-20.