Noometry

Model comparison

gpt-oss-120b vs Mistral Nemo

gpt-oss-120b is the stronger model overall, scoring 36.0 to 25.9 on the Noometry Index.

Last verified . 4 shared benchmarks.

gpt-oss-120b OpenAI

36.0

Rank #210 Confirmed

Mistral Nemo Mistral AI

25.9

Rank #332 Confirmed

Summary

  • They share 4 benchmarks with published results for both. gpt-oss-120b scores higher in 3 categories and Mistral Nemo in 2 categories; 4 gaps are clear of the uncertainty.
  • The widest gap is in knowledge, where gpt-oss-120b leads 42.3 to 12.3.
  • The biggest single-benchmark swing is GPQA Diamond: 75.8% for gpt-oss-120b and 29.9% for Mistral Nemo.
  • gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $0.15 / $0.15 for Mistral Nemo.
  • gpt-oss-120b accepts more context: 131K tokens versus 128K.

Side by side

gpt-oss-120bMistral Nemo
ProviderOpenAIMistral AI
Noometry Index36.025.9
Released2025-08-052024-07-01
WeightsOpenOpen
Context window131K128K
Max output41K128K
Input $ / M tokens$0.037$0.15
Output $ / M tokens$0.17$0.15
Results tracked4810

Sponsored placements are available on pages like this one. Advertise on Noometry

Category by category

Coding Not comparable

gpt-oss-120b: 33.2 (#251), Mistral Nemo: —

Benchmarkgpt-oss-120bMistral Nemo
SWE-bench Verified (bash only)26%—
Aider Polyglot41.8%—
SciCode36%—
WeirdML48.2%—
LMArena Coding1380—
ALE-Bench575.62—
AlgoTune1.41—

Agentic & Tool Use Mistral Nemo leads

gpt-oss-120b: 12.1 (#145), Mistral Nemo: 23.3 (#118)

Benchmarkgpt-oss-120bMistral Nemo
Terminal-Bench18.7%—
APEX-Agents4.4%—
Berkeley Function Calling Leaderboard—27.6%
BALROG—17.6%
METR Time Horizons56.6%—
Vending-Bench 2-21.53—

Reasoning Too close to call

gpt-oss-120b: 19.5 (#236), Mistral Nemo: 19.9 (#230)

Benchmarkgpt-oss-120bMistral Nemo
DTBench76.3%48.6%
Epoch Capabilities Index139.94118.63
SimpleBench22.1%—
Kagi LLM Benchmark58.6%—
CritPt1.1%—
Chess Puzzles20%—
LMArena Hard Prompts1364—
Mystery Game Puzzles2%—
LMCA22.1%—
Surface Evolver Bench25%—
PIQA—83.5%

Math gpt-oss-120b leads

gpt-oss-120b: 50.6 (#43), Mistral Nemo: 23.5 (#263)

Benchmarkgpt-oss-120bMistral Nemo
OTIS Mock AIME 2024-202588.9%—
Omni-MATH68.8%—
LMArena Math1388—
MATH Level 5—10.8%
GSM8K—84.2%

Knowledge gpt-oss-120b leads

gpt-oss-120b: 42.3 (#89), Mistral Nemo: 12.3 (#293)

Benchmarkgpt-oss-120bMistral Nemo
GPQA Diamond75.8%29.9%
MMLU-Pro79.5%—
Confabulations15.7%—
Vectara Hallucination Rate14.2%—
GPQA (HELM)68.4%—
LMArena Expert1356—
BoolQ—82.5%

Multilingual Not comparable

gpt-oss-120b: 48.2 (#142), Mistral Nemo: —

Benchmarkgpt-oss-120bMistral Nemo
LMArena Non-English1350—
LMArena Chinese1384—
LMArena French1370—
LMArena German1355—
LMArena Japanese1332—
LMArena Korean1283—
LMArena Russian1343—
LMArena Spanish1388—

Instruction Following Not comparable

gpt-oss-120b: 69.5 (#168), Mistral Nemo: —

Benchmarkgpt-oss-120bMistral Nemo
IFEval83.6%—
LMArena Instruction Following1318—

Long Context Not comparable

gpt-oss-120b: 31.4 (#273), Mistral Nemo: —

Benchmarkgpt-oss-120bMistral Nemo
Fiction.LiveBench44.4%—
LMArena Longer Query1319—

Writing & Preference gpt-oss-120b leads

gpt-oss-120b: 46.7 (#213), Mistral Nemo: 28.6 (#291)

Benchmarkgpt-oss-120bMistral Nemo
EQ-Bench Creative Writing961881
LMArena Text1366—
LMArena Creative Writing1274—
Short-Story Creative Writing77.1%—
WildBench84.5%—
LMArena Multi-Turn1340—

Frequently asked questions

Is gpt-oss-120b better than Mistral Nemo?

gpt-oss-120b is the stronger model overall, scoring 36.0 to 25.9 on the Noometry Index.

Which is cheaper, gpt-oss-120b or Mistral Nemo?

gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Mistral Nemo lists at $0.15 and $0.15.

Which has the bigger context window?

gpt-oss-120b does, with 131K tokens against 128K.

How many benchmarks do gpt-oss-120b and Mistral Nemo share?

4 benchmarks have published results for both models. gpt-oss-120b has 48 scored results on Noometry and Mistral Nemo has 10.

Related comparisons

Go deeper