Claude Opus 4.1 vs Gemma 4 31B

Change models
IndexAll categories, out of 100.
47.5 ±5.0
47.9 ±3.3 best
GapIndex points below the top.
−0.4 · no clear gap
Top
CoverageIndex weight that has results.
90%
100% best
SpeedOutput tokens per second.
12/s
35/s best
EloLMArena rating and rank.
1419
1443 best
ReleasedMonth of release.
2025-08
2026-04
Input / 1MUS dollars per 1M input tokens.
$15.00
Free best
Output / 1MUS dollars per 1M output tokens.
$75.00
Free best
Batch output / 1MBatch price per 1M output tokens.
$37.50
—
1K chats2K tokens in, 500 out, each.
$67.50
Free best
1K documents20K tokens in, 1K out, each.
$375.00
Free best
1K agent tasks200K tokens in, 20K out, each.
$4,500.00
Free best
ContextMaximum tokens in one request.
200K
256K best
AgenticMulti-step tasks with tools.
48.7 best
44.9
CodingCode writing and repair.
48.2
50.1 best
ReasoningLogic problems and puzzles.
55.5 best
46.6
MultimodalTasks with images and text.
51.1
56.9 best
KnowledgeFacts and expert knowledge.
49.4 best
44.6
MultilingualTasks in many languages.
—
47.5
InstructionTasks with strict prompt rules.
—
59.7
MathMath problems.
42.0
51.6 best

Benchmarks

3 shared
Only Claude Opus 4.1: 23Only Gemma 4 31B: 44
Claude Opus 4.1
Gemma 4 31B
76.8% best99 / 217
75.8%103 / 217
64.4%109 / 200
73.3% best94 / 200
61.1%63 / 97
61.4% best60 / 97