Skip to content

Benchmark

LMArena Elo

People compare model answers and choose which they prefer. Scores are Elo ratings. Higher ratings are better.

Models measured
3
Scores recorded
3
Sources
1
IQ weight
No weight published

Score distribution

1,435.7
Mean
1,438
Median
13.6
Std dev
1,418
10th percentile
1,451
90th percentile
1,418
Min
1,4181,451
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Gemma 4 31B ITGemma 4 Technical Report · Table 4 · blind human preference · leaderboard snapshot 2026-06-19· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.1,451
2Gemma 4 26B A4BGemma 4 Technical Report · Table 4 · blind human preference · leaderboard snapshot 2026-06-19· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.1,438
3Mistral Large 3 675b Instruct±11· Reported by Mistral AI· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.1,418

Data credits: BenchBoard by SYuan03 (github.com/SYuan03/benchboard). MIT covers its code and data organization; no results licence is inferred. Numeric relays retain the original stating-source links.