Skip to content

Benchmark

MTOB

Higher scores are better.

Models measured
3
Scores recorded
12
Sources
1
IQ weight
No weight published

Score distribution

45.3
Mean
46.2
Median
5.7
Std dev
36.6
10th percentile
52.9
90th percentile
36.3
Min
36.354.3
The band covers the middle 80% of scores. The line marks the median.

Leaderboard

#ModelScore
1Gemma 4 31B ITGemma 4 Technical Report · Table 9 · without thinking · English → KGV · full book · ~256K· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.54.3
2Gemma 4 31B ITGemma 4 Technical Report · Table 9 · without thinking · English → KGV · half book · ~128K· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.52.9
3Gemma 4 26B A4BGemma 4 Technical Report · Table 9 · without thinking · English → KGV · half book · ~128K· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.50
4Gemma 4 26B A4BGemma 4 Technical Report · Table 9 · without thinking · English → KGV · full book · ~256K· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.48.9
5Gemma 4 31B ITGemma 4 Technical Report · Table 9 · without thinking · KGV → English · half book · ~128K· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.48.6
6Gemma 4 31B ITGemma 4 Technical Report · Table 9 · without thinking · KGV → English · full book · ~256K· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.46.2
7Gemma 4 26B A4BGemma 4 Technical Report · Table 9 · without thinking · KGV → English · half book · ~128K· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.45
8Gemma 4 26B A4BGemma 4 Technical Report · Table 9 · without thinking · KGV → English · full book · ~256K· Reported by Google DeepMind· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.42.7
9Llama 4 Scouthalf-book · en→kgv· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.42.2
10Llama 4 Scoutfull-book · en→kgv· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.39.7
11Llama 4 Scouthalf-book · kgv→en· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.36.6
12Llama 4 Scoutfull-book · kgv→en· Reported by Meta· via BenchBoard docs· Reported by the model's developer. The source relaying it did not verify it.36.3

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.