Related Models
Performance
55
tokens/sec
Faster than 24% of models
0.72
seconds
Faster than 69% of models
0.72
seconds
Faster than 78% of models
Market Median
95 tok/s
42% slower
Median TTFT
1.11s
35% faster
Speed Comparison
Mistral Large 2 (Nov '24)
55 tok/s+0%
Qwen3.5 Omni Plus
55 tok/s+1%
Olmo 3.1 32B Instruct
54 tok/s-1%
Benchmarks
MMLU-Pro
13.5%
GPQA Diamond
23.7%
HLE
5.2%
LiveCodeBench
1.7%
SciCode
0.7%
TerminalBench Hard
0.0%
MATH-500
48.4%
AIME
0.0%
AIME 2025
3.3%
IFBench
19.9%
Long Context Recall
0.0%
Tau2
10.5%
Market AverageTop Score