Knowledge · Benchmark profile
A multilingual MMLU-style benchmark reported in provider evaluation tables.
Data verified 21 Jul 2026 · Methodology 1.6.0
Benchmark score on MMMLU
Interfaze Beta leads at 90.9%, followed by DeepSeek V4 Pro Base (90.3%) and Qwen3.7-Max (90.3%).
Visual analysis
Switch between model placement, score distribution and descriptive provider averages. Every view uses the same sourced leaderboard.
6 ranked models · higher is better
| Model | Rank | Provider | Score |
|---|---|---|---|
| Interfaze Beta | #1 | Interfaze | 90.9% |
| DeepSeek V4 Pro Base | #2 | DeepSeek | 90.3% |
| Qwen3.7-Max | #3 | Alibaba Cloud | 90.3% |
| Qwen3.7-Plus | #4 | Alibaba Cloud | 89% |
| DeepSeek V4 Flash Base | #5 | DeepSeek | 88.8% |
| Gemma 4 12B | #6 | 83.4% |
One best score per model · higher is better
| Rank | Model | Provider | License | Evidence use | Score |
|---|---|---|---|---|---|
| #1 | Interfaze Beta interfaze-beta | Interfaze | closed | Estimated reference | 90.9% |
| #2 | DeepSeek V4 Pro Base deepseek-v4-pro-base | DeepSeek | open | Estimated reference | 90.3% |
| #3 | Qwen3.7-Max qwen3.7-max | Alibaba Cloud | — | Reference only | 90.3% |
| #4 | Qwen3.7-Plus qwen3.7-plus | Alibaba Cloud | — | Reference only | 89% |
| #5 | DeepSeek V4 Flash Base deepseek-v4-flash-base | DeepSeek | open | Estimated reference | 88.8% |
| #6 | Gemma 4 12B gemma-4-12b | open | Estimated reference | 83.4% |
The top of this snapshot is led by Interfaze Beta at 90.9%; third place is 0.60 points behind. The top-6 spread is 7.5 points.
About MMMLU
A multilingual MMLU-style benchmark reported in provider evaluation tables. 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
A multilingual MMLU-style benchmark reported in provider evaluation tables.
Interfaze Beta by Interfaze currently leads with 90.9%.
6 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
