DataLearner logo

GPT OSS 20B Benchmark Details

GPT OSS 20B currently shows benchmark results led by AIME 2024 (3 / 62, score 96), AIME2025 (14 / 107, score 98.70), CodeForces (9 / 16, score 2516).

Benchmark Results

GPT OSS 20B

Benchmark Results

Thinking
Tool usage

General Knowledge

5 evaluations
Benchmark / mode
Score
Rank/total
MMLU
85.30
39 / 66
MMLU Pro
74
86 / 132
GPQA Diamond
71.50
109 / 187
HLE
17.30
130 / 172
HLE
10.90
143 / 172

Coding and Software Engineer

3 evaluations
Benchmark / mode
Score
Rank/total
CodeForces
2516
9 / 16
CodeForces
2230
12 / 16
SWE-bench Verified
34
106 / 112

Math and Reasoning

3 evaluations
Benchmark / mode
Score
Rank/total
AIME2025
98.70
14 / 107
AIME2025
79
60 / 107
AIME 2024
96
3 / 62

Agent Level Benchmark

1 evaluations
Benchmark / mode
Score
Rank/total
τ²-Bench
47.70
36 / 43

Instruction Following

1 evaluations
Benchmark / mode
Score
Rank/total
IF Bench
65.10
20 / 30

AI Agent - Information Search

1 evaluations
Benchmark / mode
Score
Rank/total
BrowseComp
28.30
50 / 53

Claw-style Agent Evaluation

1 evaluations
Benchmark / mode
Score
Rank/total
Pinch Bench
Thinking EnabledTools
66
34 / 37
Compare with other models