MAXIFE
We show this table for reference; we do not rank on it.
A multilingual instruction-following and understanding benchmark row published in Qwen's launch comparisons.
Benchmark score on MAXIFE — October 10, 2026
We compile the MAXIFE rows from provider self-reports and secondary reports. Qwen3.7 Max leads the table at 89.2%, followed by Qwen3.7 Plus (88.8%) and Qwen3.5 397B (88.2%). We do not use these results to rank models overall.
Qwen3.7 Max
Alibaba
Qwen3.7 Plus
Alibaba
Qwen3.5 397B
Alibaba
5 modelsMultilingualCurrentDisplay onlyUpdated October 10, 2026
Benchmark score table (5 models)
| Rank | Model / configuration | Score | Parameters (B) | Open / closed |
|---|---|---|---|---|
| 1 | Qwen3.7 MaxAlibaba | 89.2% | Not reported | Closed |
| 2 | Qwen3.7 PlusAlibaba | 88.8% | Not reported | Closed |
| 3 | Qwen3.5 397BAlibaba | 88.2% | Not reported | Open |
| 4 | Claude Opus 4.5Anthropic | 79.2% | Not reported | Closed |
| 5 | Kimi K2.5Moonshot AI | 72.8% | Not reported | Open |
Among the reported MAXIFE rows, Qwen3.7 Max is first at 89.2%. The third row is 1.0 points behind. The broader top-10 range is 16.4 points, so the table still separates the published systems.
5 models have been evaluated on MAXIFE. The benchmark falls in the Multilingual category. MAXIFE is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About MAXIFE
Year
2026
Tasks
Multilingual instruction following
Format
Cross-lingual benchmark
Difficulty
Advanced multilingual instruction following
MAXIFE appears as a high-level multilingual benchmark intended to capture both instruction compliance and language transfer. BenchLM tracks it as a display-only multilingual signal pending a fuller public benchmark specification.
Freshness and provenance
Version
MAXIFE 2026
Refresh cadence
Quarterly
Staleness state
Current
Question availability
Public benchmark set
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.
Questions
What does MAXIFE measure?
A multilingual instruction-following and understanding benchmark row published in Qwen's launch comparisons.
Which model scores highest on MAXIFE?
Qwen3.7 Max by Alibaba currently leads with a score of 89.2% on MAXIFE.
How many models are evaluated on MAXIFE?
5 AI models have published results on MAXIFE in the BenchLM catalog.
Know when it’s worth switching models
The model to choose, the cheaper alternative, and the release we would wait on.
Read a sample issueJoin 5,500+ readers.
One email each week. Unsubscribe anytime.