Gemma 4 31B vs Qwen3 235B 2507 (Reasoning)
Change modelsGemma 4 31BGoogle
Qwen3 235B 2507 (Reasoning)Alibaba
IndexAll categories, out of 100.
47.9 ±3.3 best
47.4 ±10.2
GapIndex points below the top.
Top
−0.5 · no clear gap
CoverageIndex weight that has results.
100% best
55%
SpeedOutput tokens per second.
35/s
108/s best
EloLMArena rating and rank.
1443 best
1416
ReleasedMonth of release.
2026-04
2025-07
Input / 1MUS dollars per 1M input tokens.
Free best
$0.45
Output / 1MUS dollars per 1M output tokens.
Free best
$3.50
1K chats2K tokens in, 500 out, each.
Free best
$2.65
1K documents20K tokens in, 1K out, each.
Free best
$12.50
1K agent tasks200K tokens in, 20K out, each.
Free best
$160.00
ContextMaximum tokens in one request.
256K best
128K
AgenticMulti-step tasks with tools.
44.9
—
CodingCode writing and repair.
50.1 best
45.3
ReasoningLogic problems and puzzles.
46.6
—
MultimodalTasks with images and text.
56.9
—
KnowledgeFacts and expert knowledge.
44.6
48.9 best
MultilingualTasks in many languages.
47.5
50.4 best
InstructionTasks with strict prompt rules.
59.7 best
40.0
MathMath problems.
51.6 best
49.1
Benchmarks
4 sharedOnly Gemma 4 31B: 43Only Qwen3 235B 2507 (Reasoning): 4
Gemma 4 31B
Qwen3 235B 2507 (Reasoning)