Knowledge · Benchmark profile
An independently evaluated multilingual knowledge result from Artificial Analysis.
Data verified 21 Jul 2026 · Methodology 1.6.0
Benchmark score on Artificial Analysis Global-MMLU-Lite
Gemini 3.1 Pro leads at 93.2%, followed by Claude Opus 4.6 (Adaptive) (92.2%) and Gemini 3 Pro (92.2%).
Visual analysis
Switch between model placement, score distribution and descriptive provider averages. Every view uses the same sourced leaderboard.
5 ranked models · higher is better
| Model | Rank | Provider | Score |
|---|---|---|---|
| Gemini 3.1 Pro | #1 | 93.2% | |
| Claude Opus 4.6 (Adaptive) | #2 | Anthropic | 92.2% |
| Gemini 3 Pro | #3 | 92.2% | |
| Claude Opus 4.5 Thinking | #4 | Anthropic | 91.3% |
| GPT-OSS 120B | #5 | OpenAI | 82.8% |
One best score per model · higher is better
| Rank | Model | Provider | License | Evidence use | Score |
|---|---|---|---|---|---|
| #1 | Gemini 3.1 Pro gemini-3-1-pro | closed | Estimated reference | 93.2% | |
| #2 | Claude Opus 4.6 (Adaptive) claude-opus-4-6-thinking | Anthropic | closed | Estimated reference | 92.2% |
| #3 | Gemini 3 Pro gemini-3-pro | closed | Reference only | 92.2% | |
| #4 | Claude Opus 4.5 Thinking claude-opus-4-5-thinking | Anthropic | closed | Estimated reference | 91.3% |
| #5 | GPT-OSS 120B gpt-oss-120b | OpenAI | open | Reference only | 82.8% |
The top of this snapshot is led by Gemini 3.1 Pro at 93.2%; third place is 1.0 points behind. The top-5 spread is 10.4 points.
About Artificial Analysis Global-MMLU-Lite
An independently evaluated multilingual knowledge result from Artificial Analysis. Results stay tied to the exact model variant and evaluation system. Multiple systems for the same model use the best published score on this page; overall Lumina scoring uses the median of ranking-eligible rows.
Open benchmark source ↗FAQ
An independently evaluated multilingual knowledge result from Artificial Analysis.
Gemini 3.1 Pro by Google currently leads with 93.2%.
5 models in the LuminaBench cohort have a qualifying score on this benchmark.
Related
2026 · 10 results · Reference
Artificial Analysis MMLU-Pro2026 · 4 results · Reference
Massive Multitask Language Understanding2020 · 8 results · Reference
Graduate-Level Google-Proof Q&A2023 · 70 results · Reference
SuperGPQA: Scaling LLM Evaluation Across 285 Graduate Disciplines2025 · 19 results · Reference
Massive Multitask Language Understanding Professional2024 · 42 results · Reference
