Qwen3 235B A22B Thinking 2507
Qwen3 235B Thinking is a MoE model (235B total, 22B active) optimized for complex reasoning. It generates thinking traces for deep problem solving.
Leaderboards
QUALITY
Average Score combining domain-specific Autobench scores; Higher is better
- 4.48
- 4.43
- 4.39
- 4.38
- 4.32
- 4.29
- 4.29
- 4.20
- 4.18
- 4.17
- 4.17
- 4.13
- 4.12
- 4.11
- 4.11
- 4.06
- 4.06
- 3.99
- 3.88
- 3.86
- 3.78
- 3.47
PRICE
USD cent per average answer; Lower is better
- 0.07
- 0.08
- 0.09
- 0.11
- 0.33
- 0.34
- 0.54
- 0.71
- 0.91
- 0.99
- 1.25
- 1.30
- 1.86
- 2.12
- 3.79
- 3.94
- 6.48
- 7.36
- 8.12
- 10.80
- 11.39
- 17.26
- 81.88
LATENCY
Average Latency in Seconds; Lower is better
- 20.42s
- 23.60s
- 30.08s
- 31.40s
- 38.77s
- 45.56s
- 51.84s
- 52.25s
- 61.46s
- 65.62s
- 66.78s
- 69.24s
- 75.48s
- 76.11s
- 82.80s
- 86.80s
- 89.96s
- 93.49s
- 99.62s
- 104.78s
- 110.95s
- 122.42s
- 124.57s
- 130.10s
- 136.96s
- 144.01s
- 163.15s
- 169.73s
- 171.50s
- 180.11s
- 187.43s
- 227.43s
- 247.97s
- 261.38s
- 310.39s
Performance vs. Industry Average
Intelligence
Qwen3 235B A22B Thinking 2507 is of higher intelligence compared to average (4.1), with an intelligence score of 4.2.
Price
Qwen3 235B A22B Thinking 2507 is cheaper compared to average ($4.58 per 1M Tokens) with a price of $0.32 per 1M Tokens.
Latency
Qwen3 235B A22B Thinking 2507 has a higher average latency compared to average (116.45s), with an average latency of 316.82s.
P99 Latency
Qwen3 235B A22B Thinking 2507 has a higher P99 latency compared to average (339.37s), taking 810.89s to receive the first token at P99 (TTFT).
Context Window
Qwen3 235B A22B Thinking 2507 has a smaller context window than average (351k tokens), with a context window of 262k tokens.