Qwen3 235B 2507 vs Qwen3 235B 2507 (Reasoning)
Change modelsQwen3 235B 2507Alibaba
Qwen3 235B 2507 (Reasoning)Alibaba
IndexAll categories, out of 100.
42.3 ±8.1
47.4 ±10.2 best
GapIndex points below the top.
−5.1 · no clear gap
Top
CoverageIndex weight that has results.
70% best
55%
SpeedOutput tokens per second.
48/s
108/s best
EloLMArena rating and rank.
1419 best
1416
ReleasedMonth of release.
2025-07
2025-07
Input / 1MUS dollars per 1M input tokens.
$0.14 best
$0.45
Output / 1MUS dollars per 1M output tokens.
$0.80 best
$3.50
1K chats2K tokens in, 500 out, each.
$0.68 best
$2.65
1K documents20K tokens in, 1K out, each.
$3.60 best
$12.50
1K agent tasks200K tokens in, 20K out, each.
$44.00 best
$160.00
ContextMaximum tokens in one request.
262K best
128K
AgenticMulti-step tasks with tools.
—
—
CodingCode writing and repair.
26.9
45.3 best
ReasoningLogic problems and puzzles.
35.9
—
MultimodalTasks with images and text.
—
—
KnowledgeFacts and expert knowledge.
51.2 best
48.9
MultilingualTasks in many languages.
48.8
50.4 best
InstructionTasks with strict prompt rules.
41.8 best
40.0
MathMath problems.
37.2
49.1 best
Benchmarks
7 sharedOnly Qwen3 235B 2507: 5Only Qwen3 235B 2507 (Reasoning): 1
Qwen3 235B 2507
Qwen3 235B 2507 (Reasoning)
62.6%19 / 22
64.9% best16 / 22