The Model Index
Up to four models

GPT-5.4 Nano vs Qwen 3.5 Plus (hosted 397B-A17B)

On the index (GPT-4 = 100), GPT-5.4 Nano scores 141 and Qwen 3.5 Plus (hosted 397B-A17B) 141. Side by side on the same third-party tests, with price and context. The link in your address bar shares this exact comparison.

Next to GPT-5.4 Nano
Presets
GPT-5.4 Nano
141125–157
WeightsClosed
ReleasedMar 2026
Price in / out$0.20 / $1.25
Context400K
Core tests taken4 of 9
Qwen 3.5 Plus (hosted 397B-A17B)
141124–158
WeightsClosed
ReleasedFeb 2026
Price in / out–
Context–
Core tests taken1 of 9

GPT-5.4 Nano and Qwen 3.5 Plus (hosted 397B-A17B) are too close to call (0 points apart, within the uncertainty), ahead on 0 of 1 shared core tests.

Test by testthird-party results

GPT-5.4 NanoQwen 3.5 Plus (hosted 397B-A17B)
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)GPQA Diamond (Vals AI)GPQA Diamond (Vals AI)MMLU ProMMLU ProMMMU ProMMMU ProSimpleQA VerifiedSimpleQA VerifiedMATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)Chess puzzlesChess puzzlesFrontierMath (2025 set)FrontierMath (2025 set)FrontierMath tier 4 (2025 set)FrontierMath tier 4 (2025 set)CODINGLiveCodeBenchLiveCodeBenchSWE-benchSWE-benchVibe Code Bench v1.1Vibe Code Bench v1.1AGENTSDTBenchDTBenchLMCALMCAMystery game puzzlesMystery game puzzlesPROFESSIONAL WORKCorpFin v2CorpFin v2LegalBenchLegalBenchMortgageTaxMortgageTax
Every result as a table
TestGPT-5.4 NanoQwen 3.5 Plus (hosted 397B-A17B)
Reasoning & knowledge
GPQA Diamond (Epoch AI)78.5%84.9%
GPQA Diamond (Vals AI)77.5%87.4%
MMLU Pro77.2%87.2%
MMMU Pro73.6%22.8%
SimpleQA Verified11.7%25.4%
Maths
AIME-style maths (OTIS mock)87.8%86.7%
Chess puzzles45.0%9.0%
FrontierMath (2025 set)25.9%21.0%
FrontierMath tier 4 (2025 set)6.3%2.1%
Coding
LiveCodeBench84.0%85.3%
SWE-bench69.8%71.2%
Vibe Code Bench v1.126.1%15.7%
Agents
DTBench80.3%80.5%
LMCA36.9%36.4%
Mystery game puzzles9.0%17.0%
Professional work
CorpFin v261.2%65.3%
LegalBench77.9%85.1%
MortgageTax59.1%60.8%

Tests at least two of these models have taken. Bold rows are the core tests.

This page as a chartDownload PNG