GPT-4.1 vs Qwen3 235B-A22B
Change modelsGPT-4.1OpenAI
Qwen3 235B-A22BAlibaba
IndexAll categories, out of 100.
38.0 ±3.0
38.1 ±8.8 best
GapIndex points below the top.
−0.1 · no clear gap
Top
CoverageIndex weight that has results.
100% best
55%
SpeedOutput tokens per second.
74/s best
44/s
EloLMArena rating and rank.
1383 best
1366
ReleasedMonth of release.
2025-04
2025-04
Input / 1MUS dollars per 1M input tokens.
$2.00
$0.455 best
Output / 1MUS dollars per 1M output tokens.
$8.00
$1.82 best
Batch output / 1MBatch price per 1M output tokens.
$4.00
—
1K chats2K tokens in, 500 out, each.
$8.00
$1.82 best
1K documents20K tokens in, 1K out, each.
$48.00
$10.92 best
1K agent tasks200K tokens in, 20K out, each.
$560.00
$127.40 best
ContextMaximum tokens in one request.
1.05M best
131K
AgenticMulti-step tasks with tools.
37.8
—
CodingCode writing and repair.
34.2
44.0 best
ReasoningLogic problems and puzzles.
40.4
—
MultimodalTasks with images and text.
42.1
—
KnowledgeFacts and expert knowledge.
41.2 best
41.1
MultilingualTasks in many languages.
45.1 best
42.0
InstructionTasks with strict prompt rules.
34.2 best
30.7
MathMath problems.
35.9 best
32.2
Benchmarks
14 sharedOnly GPT-4.1: 45Only Qwen3 235B-A22B: 10
GPT-4.1
Qwen3 235B-A22B