GPT-5.4 mini vs Qwen3.5 397B
Change modelsGPT-5.4 miniOpenAI
Qwen3.5 397BAlibaba
IndexAll categories, out of 100.
54.5 ±2.4 best
53.8 ±2.4
GapIndex points below the top.
Top
−0.7 · no clear gap
CoverageIndex weight that has results.
100%
100%
SpeedOutput tokens per second.
95/s best
59/s
EloLMArena rating and rank.
1412
—
ReleasedMonth of release.
2026-03
2026-02
Input / 1MUS dollars per 1M input tokens.
$0.75
$0.60 best
Output / 1MUS dollars per 1M output tokens.
$4.50
$3.60 best
Batch output / 1MBatch price per 1M output tokens.
$2.25
—
1K chats2K tokens in, 500 out, each.
$3.75
$3.00 best
1K documents20K tokens in, 1K out, each.
$19.50
$15.60 best
1K agent tasks200K tokens in, 20K out, each.
$240.00
$192.00 best
ContextMaximum tokens in one request.
400K best
128K
AgenticMulti-step tasks with tools.
56.1 best
53.3
CodingCode writing and repair.
55.1 best
53.3
ReasoningLogic problems and puzzles.
52.2 best
51.9
MultimodalTasks with images and text.
54.8
55.6 best
KnowledgeFacts and expert knowledge.
53.7
53.8 best
MultilingualTasks in many languages.
57.6 best
55.6
InstructionTasks with strict prompt rules.
52.6
55.6 best
MathMath problems.
53.9 best
53.6
Benchmarks
16 sharedOnly GPT-5.4 mini: 59Only Qwen3.5 397B: 53
GPT-5.4 mini
Qwen3.5 397B