The Model Index
Up to four models

gpt-oss-120b vs Qwen3-32B

On the index (GPT-4 = 100), gpt-oss-120b scores 129 and Qwen3-32B 129. 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-oss-120b
Presets
gpt-oss-120b
129113–145
WeightsOpen
ReleasedAug 2025
Price in / out$0.15 / $0.60
Context131K
Core tests taken3 of 9
Qwen3-32B
129113–145
WeightsOpen
ReleasedApr 2025
Price in / out$0.080 / $0.28
Context131K
Core tests taken1 of 9

gpt-oss-120b and Qwen3-32B are too close to call (0 points apart, within the uncertainty), ahead on 1 of 1 shared core tests, at 2.0× the price.

Test by testthird-party results

gpt-oss-120bQwen3-32B
0%25%50%75%100%REASONING & KNOWLEDGEGPQA Diamond (Epoch AI)GPQA Diamond (Epoch AI)Fiction.LiveBenchFiction.LiveBenchMATHSAIME-style maths (OTIS mock)AIME-style maths (OTIS mock)CODINGAider PolyglotAider PolyglotAGENTSDTBenchDTBenchLMCALMCA
Every result as a table
Testgpt-oss-120bQwen3-32B
Reasoning & knowledge
GPQA Diamond (Epoch AI)75.8%65.7%
Fiction.LiveBench44.4%74.2%
Maths
AIME-style maths (OTIS mock)88.9%66.9%
Coding
Aider Polyglot41.8%40.0%
Agents
DTBench76.3%67.5%
LMCA22.1%17.3%
Task length · METR34 sec

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

This page as a chartDownload PNG