Noometry

Model comparison

Claude Opus 4.6 vs gpt-oss-120b

Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 36.3 on the Noometry Index. gpt-oss-120b costs 142× less per token, which makes it the better buy when Claude Opus 4.6's lead doesn't matter for your workload.

Last verified . 36 shared benchmarks.

Claude Opus 4.6 Anthropic

58.2

Rank #20 Confirmed

gpt-oss-120b OpenAI

36.3

Rank #217 Confirmed

Summary

  • They share 36 benchmarks with published results for both. Claude Opus 4.6 scores higher in 9 categories and gpt-oss-120b in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in agentic & tool use, where Claude Opus 4.6 leads 51.1 to 12.2.
  • The biggest single-benchmark swing is Terminal-Bench: 79.8% for Claude Opus 4.6 and 18.7% for gpt-oss-120b.
  • gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $5 / $25 for Claude Opus 4.6.
  • Claude Opus 4.6 accepts more context: 1M tokens versus 131K.
  • gpt-oss-120b has downloadable open weights; the other is API-only.

Side by side

Claude Opus 4.6gpt-oss-120b
ProviderAnthropicOpenAI
Noometry Index58.236.3
Released2026-02-042025-08-05
WeightsProprietaryOpen
Context window1M131K
Max output128K41K
Input $ / M tokens$5$0.037
Output $ / M tokens$25$0.17
Results tracked6848

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

Category by category

Coding Claude Opus 4.6 leads

Claude Opus 4.6: 57.2 (#20), gpt-oss-120b: 33.5 (#256)

BenchmarkClaude Opus 4.6gpt-oss-120b
SWE-bench Verified (bash only)75.6%26%
WeirdML78%48.2%
LMArena Coding15361380
ALE-Bench996.5575.62
AlgoTune1.471.41
SWE-bench Verified78.7%—
FrontierCode26.6%—
Aider Polyglot—41.8%
LMArena WebDev1547—
SWE-bench Multilingual72%—
SciCode—36%
GSO41.2%—

Agentic & Tool Use Claude Opus 4.6 leads

Claude Opus 4.6: 51.1 (#4), gpt-oss-120b: 12.2 (#153)

BenchmarkClaude Opus 4.6gpt-oss-120b
Terminal-Bench79.8%18.7%
APEX-Agents46.3%4.4%
METR Time Horizons78.9%56.6%
Vending-Bench 28,018-21.53
Remote Labor Index4.2%—
τ²-bench Banking27.3%—
Cybench93%—
DeepResearch Bench55.3%—
GBAEval44.1%—
LMArena Search1253—

Reasoning Claude Opus 4.6 leads

Claude Opus 4.6: 57.8 (#23), gpt-oss-120b: 20.0 (#245)

BenchmarkClaude Opus 4.6gpt-oss-120b
SimpleBench67.6%22.1%
Kagi LLM Benchmark83.6%58.6%
Chess Puzzles17%20%
LMArena Hard Prompts15271364
Mystery Game Puzzles25%2%
DTBench91.2%76.3%
LMCA55.8%22.1%
Epoch Capabilities Index155.24139.93
ARC-AGI-269.2%—
NYT Connections (extended)92.1%—
ARC-AGI-194%—
CritPt—1.1%
EnigmaEval7.6%—
Thematic Generalization80.6%—
EBR-Bench12.7%—
Surface Evolver Bench—25%
ForecastBench60—

Math Claude Opus 4.6 leads

Claude Opus 4.6: 63.0 (#31), gpt-oss-120b: 52.5 (#50)

BenchmarkClaude Opus 4.6gpt-oss-120b
OTIS Mock AIME 2024-202594.4%88.9%
LMArena Math15191389
FrontierMath (Tiers 1-3)66%—
FrontierMath Tier 426.8%—
MathArena Final-Answer Competitions78.5%—
ProofBench50%—
Omni-MATH—68.8%
FrontierMath (Feb 2025 set)40.7%—
FrontierMath Tier 4 (v1)22.9%—

Knowledge Claude Opus 4.6 leads

Claude Opus 4.6: 61.9 (#26), gpt-oss-120b: 42.4 (#96)

BenchmarkClaude Opus 4.6gpt-oss-120b
GPQA Diamond90.5%75.8%
Vectara Hallucination Rate12.2%14.2%
LMArena Expert15461356
Humanity's Last Exam34.4%—
SimpleQA Verified47%—
MMLU-Pro—79.5%
Confabulations—15.7%
GPQA (HELM)—68.4%

Multimodal Not comparable

Claude Opus 4.6: 37.3 (#74), gpt-oss-120b: —

BenchmarkClaude Opus 4.6gpt-oss-120b
LMArena Vision1316—
Furniture Assembly28.3%—
LMArena Document1507—

Multilingual Claude Opus 4.6 leads

Claude Opus 4.6: 57.9 (#6), gpt-oss-120b: 48.0 (#147)

BenchmarkClaude Opus 4.6gpt-oss-120b
LMArena Non-English14891351
LMArena Chinese15511385
LMArena French15131369
LMArena German15021353
LMArena Japanese14841331
LMArena Korean14641282
LMArena Russian14971343
LMArena Spanish15101389

Instruction Following Claude Opus 4.6 leads

Claude Opus 4.6: 79.5 (#4), gpt-oss-120b: 69.3 (#173)

BenchmarkClaude Opus 4.6gpt-oss-120b
LMArena Instruction Following15231318
IFEval—83.6%

Long Context Claude Opus 4.6 leads

Claude Opus 4.6: 48.1 (#13), gpt-oss-120b: 31.4 (#278)

BenchmarkClaude Opus 4.6gpt-oss-120b
LMArena Longer Query15201319
Fiction.LiveBench—44.4%
CL-bench20.7%—
CL-bench Life17%—

Writing & Preference Claude Opus 4.6 leads

Claude Opus 4.6: 73.5 (#10), gpt-oss-120b: 46.5 (#217)

BenchmarkClaude Opus 4.6gpt-oss-120b
LMArena Text15031365
LMArena Creative Writing15051275
EQ-Bench Creative Writing1809961
LMArena Multi-Turn15131340
Short-Story Creative Writing—77.1%
WildBench—84.5%
EQ-Bench 41223—

Frequently asked questions

Is Claude Opus 4.6 better than gpt-oss-120b?

Claude Opus 4.6 is the stronger model overall, scoring 58.2 to 36.3 on the Noometry Index. gpt-oss-120b costs 142× less per token, which makes it the better buy when Claude Opus 4.6's lead doesn't matter for your workload.

Which is cheaper, Claude Opus 4.6 or gpt-oss-120b?

gpt-oss-120b is cheaper. It lists at $0.037 per million input tokens and $0.17 per million output tokens; Claude Opus 4.6 lists at $5 and $25.

Is Claude Opus 4.6 or gpt-oss-120b better for coding?

Claude Opus 4.6 scores higher on coding benchmarks: 57.2 versus 33.5 in the Noometry coding category.

Which has the bigger context window?

Claude Opus 4.6 does, with 1M tokens against 131K.

How many benchmarks do Claude Opus 4.6 and gpt-oss-120b share?

36 benchmarks have published results for both models. Claude Opus 4.6 has 68 scored results on Noometry and gpt-oss-120b has 48.

Related comparisons

Go deeper