GPT-5 nano vs Qwen3 235B 2507
Change modelsGPT-5 nanoOpenAI
Qwen3 235B 2507Alibaba
IndexAll categories, out of 100.
41.9 ±6.2
42.3 ±8.1 best
GapIndex points below the top.
−0.4 · no clear gap
Top
CoverageIndex weight that has results.
75% best
70%
SpeedOutput tokens per second.
81/s best
48/s
EloLMArena rating and rank.
1320
1419 best
ReleasedMonth of release.
2025-08
2025-07
Input / 1MUS dollars per 1M input tokens.
$0.05 best
$0.14
Output / 1MUS dollars per 1M output tokens.
$0.40 best
$0.80
Batch output / 1MBatch price per 1M output tokens.
$0.20
—
1K chats2K tokens in, 500 out, each.
$0.30 best
$0.68
1K documents20K tokens in, 1K out, each.
$1.40 best
$3.60
1K agent tasks200K tokens in, 20K out, each.
$18.00 best
$44.00
ContextMaximum tokens in one request.
400K best
262K
AgenticMulti-step tasks with tools.
—
—
CodingCode writing and repair.
37.2 best
26.9
ReasoningLogic problems and puzzles.
42.6 best
35.9
MultimodalTasks with images and text.
47.5
—
KnowledgeFacts and expert knowledge.
37.4
51.2 best
MultilingualTasks in many languages.
44.5
48.8 best
InstructionTasks with strict prompt rules.
—
41.8
MathMath problems.
45.8 best
37.2
Benchmarks
4 sharedOnly GPT-5 nano: 36Only Qwen3 235B 2507: 8
GPT-5 nano
Qwen3 235B 2507