Compare · ModelsLive · 2 picked · head to head
gpt-oss-120b vs GPT-4.1 Mini
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
gpt-oss-120b wins on 10/11 benchmarks
gpt-oss-120b wins 10 of 11 shared benchmarks. Leads in coding · knowledge · math.
Category leads
coding·gpt-oss-120bknowledge·gpt-oss-120blanguage·GPT-4.1 Minimath·gpt-oss-120breasoning·gpt-oss-120b
Hype vs Reality
Attention vs performance
gpt-oss-120b
#108 by perf·no signal
GPT-4.1 Mini
#118 by perf·no signal
Best value
gpt-oss-120b
9.6x better value than GPT-4.1 Mini
gpt-oss-120b
428.3 pts/$
$0.11/M
GPT-4.1 Mini
44.5 pts/$
$1.00/M
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
OpenAI
$840.0B·Tier 1
Head to head
11 benchmarks · 2 models
gpt-oss-120bGPT-4.1 Mini
Aider polyglot
gpt-oss-120b leads by +9.4
Aider Polyglot · measures how well AI models can edit code across multiple programming languages using the Aider coding assistant framework.
gpt-oss-120b
41.8
GPT-4.1 Mini
32.4
Fiction.LiveBench
Fiction.LiveBench · a continuously updated benchmark using recently published fiction to test reading comprehension and reasoning, preventing data contamination.
gpt-oss-120b
44.4
GPT-4.1 Mini
44.4
GPQA diamond
gpt-oss-120b leads by +13.2
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
gpt-oss-120b
67.7
GPT-4.1 Mini
54.5
HELM · GPQA
gpt-oss-120b leads by +7.0
gpt-oss-120b
68.4
GPT-4.1 Mini
61.4
HELM · IFEval
GPT-4.1 Mini leads by +6.8
gpt-oss-120b
83.6
GPT-4.1 Mini
90.4
HELM · MMLU-Pro
gpt-oss-120b leads by +1.2
gpt-oss-120b
79.5
GPT-4.1 Mini
78.3
HELM · Omni-MATH
gpt-oss-120b leads by +19.7
gpt-oss-120b
68.8
GPT-4.1 Mini
49.1
HELM · WildBench
gpt-oss-120b leads by +0.7
gpt-oss-120b
84.5
GPT-4.1 Mini
83.8
OTIS Mock AIME 2024-2025
gpt-oss-120b leads by +44.2
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
gpt-oss-120b
88.9
GPT-4.1 Mini
44.7
SWE-Bench Verified (Bash Only)
gpt-oss-120b leads by +2.1
SWE-Bench Verified (Bash Only) · a curated subset of SWE-bench where models fix real Python repository bugs using only bash commands, no agent frameworks.
gpt-oss-120b
26.0
GPT-4.1 Mini
23.9
WeirdML
gpt-oss-120b leads by +10.6
WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns.
gpt-oss-120b
48.2
GPT-4.1 Mini
37.6
Full benchmark table
| Benchmark | gpt-oss-120b | GPT-4.1 Mini |
|---|---|---|
Aider polyglot Aider Polyglot · measures how well AI models can edit code across multiple programming languages using the Aider coding assistant framework. | 41.8 | 32.4 |
Fiction.LiveBench Fiction.LiveBench · a continuously updated benchmark using recently published fiction to test reading comprehension and reasoning, preventing data contamination. | 44.4 | 44.4 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 67.7 | 54.5 |
HELM · GPQA | 68.4 | 61.4 |
HELM · IFEval | 83.6 | 90.4 |
HELM · MMLU-Pro | 79.5 | 78.3 |
HELM · Omni-MATH | 68.8 | 49.1 |
HELM · WildBench | 84.5 | 83.8 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 88.9 | 44.7 |
SWE-Bench Verified (Bash Only) SWE-Bench Verified (Bash Only) · a curated subset of SWE-bench where models fix real Python repository bugs using only bash commands, no agent frameworks. | 26.0 | 23.9 |
WeirdML WeirdML · tests models on unusual and adversarial machine learning tasks that require creative problem-solving beyond standard patterns. | 48.2 | 37.6 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.04 | $0.18 | 131K tokens (~66 books) | $0.74 | |
| $0.40 | $1.60 | 1.0M tokens (~524 books) | $7.00 |
People also compared