Skip to main content
BenchLM
Advertise

Benchmark profile

Vals MGSM (MGSM)

A multilingual benchmark for mathematical questions.

Data verified

How BenchLM shows MGSM

BenchLM mirrors the public Vals AI MGSM leaderboard captured from https://www.vals.ai/benchmarks/mgsm and updated by Vals on January 9, 2026. The snapshot preserves overall scores, uncertainty, latency, cost-per-test metadata, and task-level scores where Vals publishes them.

MGSM is display only on BenchLM. Vals proprietary or Vals-hosted aggregate views are useful context, but BenchLM does not use them as weighted ranking inputs or as a replacement for benchmark-native source records.

75 Vals rows12 task viewspublic datasetTasks: Overall, English, Japanese, Chinese, BengaliDisplay only
MGSM on Vals AIVals methodologyVals home

MGSM score on MGSM — January 9, 2026

BenchLM mirrors the published mgsm score view for MGSM. Claude Opus 4.5 20251101 Thinking leads the public snapshot at 95.20% , followed by Claude Opus 4.5 (94.76%) and Claude Opus 4.1 20250805 Thinking (94.44%). BenchLM does not use these results to rank models overall.

1

Claude Opus 4.5 20251101 Thinking

Anthropic

anthropic/claude-opus-4-5-20251101-thinking

95.20%
Overall —
2

Claude Opus 4.5

Anthropic

anthropic/claude-opus-4-5-20251101

94.76%
Overall —
3

Claude Opus 4.1 20250805 Thinking

Anthropic

anthropic/claude-opus-4-1-20250805-thinking

94.44%
Overall —
75 modelsExternal benchmark mirrorsCurrentDisplay onlyUpdated January 9, 2026

MGSM score table (75 models)

Score
1
Claude Opus 4.5 20251101 ThinkingAnthropic
95.20%
2
Claude Opus 4.5Anthropic
94.76%
3
Claude Opus 4.1 20250805 ThinkingAnthropic
94.44%
4
Claude Sonnet 4.5 20250929 ThinkingAnthropic
94.33%
5
Claude Opus 4.1Anthropic
94.22%
6
GPT-5.2OpenAI
94.00%
7
Gemini 3 Pro PreviewGoogle
93.93%
8
Claude Opus 4Anthropic
93.78%
9
O4 MiniOpenAI
93.42%
10
Gemini 3 Flash PreviewGoogle
93.31%
11
Claude Sonnet 4Anthropic
93.02%
12
GPT-5.1OpenAI
92.98%
13
Claude 3.7 Sonnet 20250219 ThinkingAnthropic
92.98%
14
GPT-5OpenAI
92.84%
15
Claude 3.5 SonnetAnthropic
92.58%
16
GPT-5 MiniOpenAI
92.58%
17
Qwen3 235b A22bFireworks AI
92.47%
18
Llama4 Maverick Instruct BasicFireworks
92.44%
19
Claude 3.7 SonnetAnthropic
92.40%
20
DeepSeek R1Fireworks AI
92.25%
21
Claude Haiku 4.5 20251001 ThinkingAnthropic
92.15%
22
DeepSeek V3Fireworks AI
92.15%
23
Qwen3 Max PreviewAlibaba
92.15%
24
GPT Oss 120bFireworks AI
92.04%
25
Qwen3 MaxAlibaba
91.82%
26
O3OpenAI
91.75%
27
DeepSeek V3 0324Fireworks AI
91.67%
28
Grok 3SpaceXAI
91.35%
29
O3 MiniOpenAI
91.35%
30
Meta Llama Llama 3.3 70B Instruct TurboTogether AI
91.09%
31
Moonshotai Kimi K2 InstructTogether AI
90.95%
32
Grok 4 0709SpaceXAI
90.91%
33
Grok 4 Fast ReasoningSpaceXAI
90.87%
34
Mistral Medium 2505Mistral AI
90.87%
35
DeepSeek V3p2Fireworks
90.87%
36
Claude Sonnet 4 20250514 ThinkingAnthropic
90.87%
37
GLM 4.5Zhipu AI
90.84%
38
GPT-4oOpenAI
90.69%
39
Grok 3 Mini Fast High ReasoningSpaceXAI
90.44%
40
GPT-4oOpenAI
90.36%
41
Grok 3 Mini Fast Low ReasoningSpaceXAI
90.36%
42
Kimi K2 ThinkingMoonshot AI
90.15%
43
Gemini 2.5 Flash Preview 09 2025Google
89.85%
44
Gemini 2.5 Flash Preview 09 2025 ThinkingGoogle
89.82%
45
GLM 4.6Zhipu AI
89.75%
46
Gemini 2.5 Flash Lite Preview 09 2025Google
89.53%
47
Grok 4.1 Fast ReasoningSpaceXAI
89.53%
48
O1OpenAI
89.31%
49
GPT-5 NanoOpenAI
89.31%
50
Gemini 1.5 Pro 002Google
89.20%
51
Gemini 2.0 Flash 001Google
89.02%
52
GPT Oss 20bFireworks AI
89.02%
53
Gemini 2.5 Flash Lite Preview 09 2025 ThinkingGoogle
88.40%
54
GLM 4.7Zhipu AI
88.18%
55
Grok 4 Fast Non ReasoningSpaceXAI
88.00%
56
Meta Llama Llama 4 Scout 17B 16E InstructTogether AI
87.96%
57
MiniMax M2.1MiniMax
87.85%
58
GPT-4.1 MiniOpenAI
87.78%
59
GPT-4.1OpenAI
87.67%
60
Grok 4.1 Fast Non ReasoningSpaceXAI
87.56%
61
Mistral Large 2411Mistral AI
87.24%
62
Gemini 1.5 Flash 002Google
86.58%
63
Magistral Small 2509Mistral AI
86.25%
64
GPT-4o MiniOpenAI
86.18%
65
Grok 2 1212SpaceXAI
86.15%
66
DeepSeek V3p2 ThinkingFireworks
86.04%
67
Command A 03 2025Cohere
85.71%
68
Mistral Large 2512Mistral AI
85.42%
69
Claude 3.5 HaikuAnthropic
84.62%
70
Mistral Small 2503Mistral AI
84.22%
71
Mistral Small 2402Mistral AI
83.96%
72
Magistral Medium 2509Mistral AI
74.62%
73
Jamba Large 1.6AI21 Labs
71.24%
74
GPT-4.1 NanoOpenAI
69.27%
75
Jamba Mini 1.6AI21 Labs
41.71%

The published MGSM snapshot places Claude Opus 4.5 20251101 Thinking first at 95.20%. The third row is 0.76 points behind. The broader top-10 range is 1.89 points, so many of the published results sit in a relatively narrow band.

75 models have been evaluated on MGSM. The benchmark falls in the External benchmark mirrors category. We keep external benchmark mirrors separate from the weighted global scoring system, so these results remain source-specific evidence. MGSM is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.

About MGSM

Year

2026

Tasks

Multilingual grade-school math questions

Format

Accuracy score

Difficulty

Multilingual mathematical reasoning

BenchLM mirrors the public Vals AI MGSM leaderboard as display-only external evidence. The captured snapshot preserves overall scores, task-level scores where Vals publishes them, uncertainty, latency, and cost-per-test metadata. It is excluded from BenchLM weighted rankings.

MGSMPublic benchmark source

BenchLM freshness & provenance

Version

MGSM 2026

Refresh cadence

Quarterly

Staleness state

Current

Question availability

Public benchmark set

CurrentDisplay only

BenchLM uses freshness metadata to decide whether a benchmark should still be treated as a strong differentiator, a benchmark to watch, or a display-only reference. For the full scoring policy, see the BenchLM methodology page.

FAQ

What does MGSM measure?

A multilingual benchmark for mathematical questions.

Which model leads the published MGSM snapshot?

Claude Opus 4.5 20251101 Thinking currently leads the published MGSM snapshot with 95.20% mgsm score. BenchLM shows this benchmark for display only and does not use it in overall rankings.

How many models are evaluated on MGSM?

75 AI models are included in BenchLM's mirrored MGSM snapshot, based on the public leaderboard captured on January 9, 2026.

Last updated: January 9, 2026 · mirrored from the public benchmark leaderboard

Choose a model with this week’s evidence

Join 2,000+ readers for ranking moves, pricing changes, and the claims that still need proof.

One email each week. Unsubscribe anytime.