Nejumi 4 - MT-Bench (Japanese) - Math: leaderboard
Japanese MT-Bench questions in the math category, two-turn answers rated 1-10 by GPT-4.1 as judge in Nejumi Leaderboard 4 (Weights & Biases Japan). Nejumi stores ratings divided by 10; the board multiplies by 100 (10-100), the scale of Nejumi 4 - MT-Bench (Japanese). Higher is better.
Metric: Judge rating (1-10, x10). Source: nejumi.ai. Saturation forecast: Estimated already saturated. 145 models tracked.
Top models
| # | Model | Score | Overall rank |
|---|---|---|---|
| 1 | GPT-4.1 Mini | 100 | #363 |
| 2 | Gemini 3 Pro (Preview) | 100 | #71 |
| 3 | Gemma 4 31B (IT) | 100 | #178 |
| 4 | Gemini 3 Flash (Preview) | 100 | #90 |
| 5 | Gemini 3.5 Flash | 100 | #66 |
| 6 | Gemma 4 26B A4B (IT) | 100 | #293 |
| 7 | O3 (2025-04-16) | 100 | #125 |
| 8 | gemma-4-E4B-it | 100 | #577 |
| 9 | Gemini 3.1 Flash Lite (Preview) | 100 | #201 |
| 10 | Kimi K3 (Max) | 100 | #35 (Kimi K3) |
| 11 | Claude Opus 5 (Max) | 100 | #16 (Claude Opus 5) |
| 12 | GLM-5.3 Flash (Max) | 100 | #77 (GLM-5.3 Flash) |
| 13 | Solar Pro 4 | 100 | #230 |
| 14 | O3 (2025-04-16) (High) | 100 | #125 (O3 (2025-04-16)) |
| 15 | Qwen 3.5 27B (Thinking) | 100 | #192 (Qwen 3.5 27B) |
No result here: #3 Claude Opus 5.5, #6 GPT-6 Astra, #7 GPT-6.1 Sol.
Interactive version: theaggregate.ai/benchmark?slug=nejumi-4-mt-bench-japanese-math · How It Works · Data refreshed daily, snapshot 2026-11-05.