The Model Index
Up to four models

Qwen3.8-Max vs GPT-5.4

On the index (GPT-4 = 100), Qwen3.8-Max scores 167 and GPT-5.4 166. 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 Qwen3.8-Max
Presets
Qwen3.8-Max
167151–183
WeightsClosed
ReleasedAug 2026
Price in / out–
Context–
Core tests taken3 of 9
GPT-5.4
166150–182
WeightsClosed
ReleasedMar 2026
Price in / out$2.5 / $15
Context1.05M
Core tests taken7 of 9

Qwen3.8-Max and GPT-5.4 are too close to call (1 point apart, within the uncertainty), ahead on 1 of 3 shared core tests.

Test by testthird-party results

Qwen3.8-MaxGPT-5.4
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)SimpleQA VerifiedSimpleQA VerifiedMATHSFrontierMath (tiers 1-3)FrontierMath (tiers 1-3)AIME-style maths (OTIS mock)AIME-style maths (OTIS mock)Chess puzzlesChess puzzlesFrontierMath (tier 4)FrontierMath (tier 4)CODINGDeepSWEDeepSWEMirrorCodeMirrorCodeAGENTSAPEX-AgentsAPEX-AgentsDTBenchDTBenchLMCALMCAMystery game puzzlesMystery game puzzles
Every result as a table
TestQwen3.8-MaxGPT-5.4
Reasoning & knowledge
GPQA Diamond (Epoch AI)92.7%93.3%
SimpleQA Verified45.8%45.1%
Maths
FrontierMath (tiers 1-3)74.7%78.6%
AIME-style maths (OTIS mock)99.4%97.8%
Chess puzzles46.0%48.0%
FrontierMath (tier 4)46.3%49.0%
Coding
DeepSWE57.5%51.8%
MirrorCode52.2%23.3%
Agents
APEX-Agents63.3%52.4%
DTBench92.0%94.4%
LMCA46.2%52.0%
Mystery game puzzles38.0%37.0%
Task length · METR45 sec

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

This page as a chartDownload PNG