Best AI for multilingual tasks (Nov 2026)
Reasoning in languages other than English. The leaders, with sources, are summarised below the chart.
MGSM
Maths questions in multiple languages.
Vals AI does not publish a cost per test for this benchmark, so there is no performance-vs-cost chart. Showing the ranking instead.
Highest reported score: Claude Opus 4.5 (Thinking) (Anthropic) at 95.20%.
Accuracy, highest first. Position is the source’s published rank.
- 1Claude Opus 4.5 (Thinking) Anthropic95.20%
- 2Claude Opus 4.5 (Nonthinking) Anthropic94.76%
- 3Claude Opus 4.1 (Thinking) Anthropic94.44%
- 4Claude Sonnet 4.5 (Thinking) Anthropic94.33%
- 5Claude Opus 4.1 (Nonthinking) Anthropic94.22%
- 6GPT 5.2 OpenAI94.00%
- 7Gemini 3 Pro (11/25) Google93.93%
- 8Claude Opus 4 (Nonthinking) Anthropic93.78%
- 9o4 Mini OpenAI93.42%
- 10Gemini 3 Flash (12/25) Google93.31%
- 11Claude Sonnet 4 (Nonthinking) Anthropic93.02%
- 12GPT 5.1 OpenAI92.98%
- 13Claude 3.7 Sonnet (Thinking) Anthropic92.98%
- 14GPT 5 OpenAI92.84%
- 15Claude 3.5 Sonnet Latest Anthropic92.58%
- 16GPT 5 Mini OpenAI92.58%
- 17Qwen 3 (235B) Alibaba92.47%
- 18Llama 4 Maverick Meta92.44%
- 19Claude 3.7 Sonnet (Nonthinking) Anthropic92.40%
- 20DeepSeek R1 DeepSeek92.25%
- 21Claude Haiku 4.5 (Thinking) Anthropic92.15%
- 22DeepSeek V3 DeepSeek92.15%
- 23Qwen 3 Max Preview Alibaba92.15%
- 24GPT OSS 120B OpenAI92.04%
- 25Qwen 3 Max Alibaba91.82%
| 1 | Claude Opus 4.5 (Thinking) | Anthropic | 95.20% |
|---|---|---|---|
| 2 | Claude Opus 4.5 (Nonthinking) | Anthropic | 94.76% |
| 3 | Claude Opus 4.1 (Thinking) | Anthropic | 94.44% |
| 4 | Claude Sonnet 4.5 (Thinking) | Anthropic | 94.33% |
| 5 | Claude Opus 4.1 (Nonthinking) | Anthropic | 94.22% |
| 6 | GPT 5.2 | OpenAI | 94.00% |
| 7 | Gemini 3 Pro (11/25) | 93.93% | |
| 8 | Claude Opus 4 (Nonthinking) | Anthropic | 93.78% |
| 9 | o4 Mini | OpenAI | 93.42% |
| 10 | Gemini 3 Flash (12/25) | 93.31% | |
| 11 | Claude Sonnet 4 (Nonthinking) | Anthropic | 93.02% |
| 12 | GPT 5.1 | OpenAI | 92.98% |
| 13 | Claude 3.7 Sonnet (Thinking) | Anthropic | 92.98% |
| 14 | GPT 5 | OpenAI | 92.84% |
| 15 | Claude 3.5 Sonnet Latest | Anthropic | 92.58% |
| 16 | GPT 5 Mini | OpenAI | 92.58% |
| 17 | Qwen 3 (235B) | Alibaba | 92.47% |
| 18 | Llama 4 Maverick | Meta | 92.44% |
| 19 | Claude 3.7 Sonnet (Nonthinking) | Anthropic | 92.40% |
| 20 | DeepSeek R1 | DeepSeek | 92.25% |
| 21 | Claude Haiku 4.5 (Thinking) | Anthropic | 92.15% |
| 22 | DeepSeek V3 | DeepSeek | 92.15% |
| 23 | Qwen 3 Max Preview | Alibaba | 92.15% |
| 24 | GPT OSS 120B | OpenAI | 92.04% |
| 25 | Qwen 3 Max | Alibaba | 91.82% |
Source: Vals AI · leaderboard dated 9 Jan 2026 · checked 17 Nov 2026 · archived (no longer updated)
Prompts to try with these models
All prompts →Results from published AI leaderboards. Compare models within each benchmark; scores from different tests aren’t directly comparable. How we collect these results
Highest reported scores
As of 9 Jan 2026, the highest reported score on MGSM is Claude Opus 4.5 (Thinking) (Anthropic) at 95.20%, per Vals AI. The source no longer updates this leaderboard.
About this benchmark
MGSM
Maths questions in multiple languages.
As of 9 Jan 2026, the highest reported score on MGSM is Claude Opus 4.5 (Thinking) (Anthropic) at 95.20%, per Vals AI. The source no longer updates this leaderboard.
Questions people ask
Which AI has the highest reported scores for multilingual tasks?
As of 9 Jan 2026, the highest reported score on MGSM is Claude Opus 4.5 (Thinking) (Anthropic) at 95.20%, per Vals AI. The source no longer updates this leaderboard.
Which benchmarks are on this page?
MGSM (run by Vals AI): Maths questions in multiple languages.
How recent are these results?
MGSM: leaderboard dated 9 Jan 2026, no longer updated by the source; we last checked it on 17 Nov 2026.
Does ChatJudge run these tests?
No. Every score is copied as published by the leaderboard that ran it, with a link to the source. Scores from different benchmarks are not directly comparable.
