INCLUDE
We show this table for reference; we do not rank on it.
A multilingual benchmark used in provider tables to measure inclusive language coverage and cross-lingual understanding beyond common high-resource languages.
Benchmark score on INCLUDE — October 10, 2026
We compile the INCLUDE rows from provider self-reports and secondary reports. Claude Opus 5 leads the table at 89.8%, followed by Claude Opus 4.8 (87.6%) and Qwen3.7 Max (86.2%). We do not use these results to rank models overall.
Claude Opus 5
Anthropic
Claude Opus 4.8
Anthropic
Qwen3.7 Max
Alibaba
7 modelsMultilingualCurrentDisplay onlyUpdated October 10, 2026
Benchmark score table (7 models)
| Rank | Model / configuration | Score | Parameters (B) | Open / closed |
|---|---|---|---|---|
| 1 | Claude Opus 5Anthropic | 89.8% | Not reported | Closed |
| 2 | Claude Opus 4.8Anthropic | 87.6% | Not reported | Closed |
| 3 | Qwen3.7 MaxAlibaba | 86.2% | Not reported | Closed |
| 4 | Claude Opus 4.5Anthropic | 86.2% | Not reported | Closed |
| 5 | Qwen3.5 397BAlibaba | 85.6% | Not reported | Open |
| 6 | Kimi K2.5Moonshot AI | 83.3% | Not reported | Open |
| 7 | Qwen3.7 PlusAlibaba | 83.0% | Not reported | Closed |
Among the reported INCLUDE rows, Claude Opus 5 is first at 89.8%. The third row is 3.6 points behind. The broader top-10 range is 6.8 points, so many of the published results sit in a relatively narrow band.
7 models have been evaluated on INCLUDE. The benchmark falls in the Multilingual category. INCLUDE is currently displayed for reference but excluded from the scoring formula, so it does not directly affect overall rankings.
About INCLUDE
Year
2026
Tasks
Cross-lingual understanding
Format
Multilingual benchmark
Difficulty
Broad multilingual capability
INCLUDE is useful as a multilingual breadth check because it is intended to reward stronger performance across a wider and less English-centric language set than basic translated math benchmarks.
Freshness and provenance
Version
INCLUDE 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 INCLUDE measure?
A multilingual benchmark used in provider tables to measure inclusive language coverage and cross-lingual understanding beyond common high-resource languages.
Which model scores highest on INCLUDE?
Claude Opus 5 by Anthropic currently leads with a score of 89.8% on INCLUDE.
How many models are evaluated on INCLUDE?
7 AI models have published results on INCLUDE 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.