Noometry

Model comparison

Claude Sonnet 4.6 vs gpt-oss-120b

Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 36.3 on the Noometry Index. gpt-oss-120b costs 85× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.

Last verified . 33 shared benchmarks.

Claude Sonnet 4.6 Anthropic

50.3

Rank #50 Confirmed

gpt-oss-120b OpenAI

36.3

Rank #217 Confirmed

Summary

  • They share 33 benchmarks with published results for both. Claude Sonnet 4.6 scores higher in 9 categories and gpt-oss-120b in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in agentic & tool use, where Claude Sonnet 4.6 leads 39.1 to 12.2.
  • The biggest single-benchmark swing is APEX-Agents: 43% for Claude Sonnet 4.6 and 4.4% for gpt-oss-120b.
  • gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $3 / $15 for Claude Sonnet 4.6.
  • Claude Sonnet 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 Sonnet 4.6gpt-oss-120b
ProviderAnthropicOpenAI
Noometry Index50.336.3
Released2026-02-172025-08-05
WeightsProprietaryOpen
Context window1M131K
Max output128K41K
Input $ / M tokens$3$0.037
Output $ / M tokens$15$0.17
Results tracked5748

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

Category by category

Coding Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 46.3 (#67), gpt-oss-120b: 33.5 (#256)

BenchmarkClaude Sonnet 4.6gpt-oss-120b
SciCode46.8%36%
WeirdML66.1%48.2%
LMArena Coding15041380
ALE-Bench1,327575.62
SWE-bench Verified75.2%—
DeepSWE29.9%—
FrontierCode24.3%—
SWE-bench Verified (bash only)—26%
Aider Polyglot—41.8%
LMArena WebDev1522—
AlgoTune—1.41

Agentic & Tool Use Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 39.1 (#28), gpt-oss-120b: 12.2 (#153)

BenchmarkClaude Sonnet 4.6gpt-oss-120b
Terminal-Bench53.4%18.7%
APEX-Agents43%4.4%
Vending-Bench 27,204-21.53
OSWorld 2.09.3%—
DeepResearch Bench54.9%—
OSWorld72.1%—
ExploitBench23.6%—
GBAEval48.8%—
GDP.pdf18%—
LMArena Search1221—
METR Time Horizons—56.6%

Reasoning Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 46.1 (#45), gpt-oss-120b: 20.0 (#245)

BenchmarkClaude Sonnet 4.6gpt-oss-120b
CritPt3.1%1.1%
Chess Puzzles13%20%
LMArena Hard Prompts14841364
Mystery Game Puzzles16%2%
DTBench89.9%76.3%
LMCA46.5%22.1%
Epoch Capabilities Index152.24139.93
ARC-AGI-260.4%—
SimpleBench—22.1%
Kagi LLM Benchmark—58.6%
NYT Connections (extended)80.9%—
ARC-AGI-186.5%—
Thematic Generalization76.3%—
Surface Evolver Bench—25%
ForecastBench62—

Math Too close to call

Claude Sonnet 4.6: 52.9 (#49), gpt-oss-120b: 52.5 (#50)

BenchmarkClaude Sonnet 4.6gpt-oss-120b
OTIS Mock AIME 2024-202585.8%88.9%
LMArena Math14621389
ProofBench45%—
Omni-MATH—68.8%
FrontierMath (Feb 2025 set)32.4%—
FrontierMath Tier 4 (v1)8.3%—

Knowledge Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 51.7 (#65), gpt-oss-120b: 42.4 (#96)

BenchmarkClaude Sonnet 4.6gpt-oss-120b
GPQA Diamond87.4%75.8%
Vectara Hallucination Rate10.6%14.2%
LMArena Expert15001356
SimpleQA Verified35.5%—
MMLU-Pro—79.5%
Confabulations—15.7%
GPQA (HELM)—68.4%

Multimodal Not comparable

Claude Sonnet 4.6: 38.0 (#68), gpt-oss-120b: —

BenchmarkClaude Sonnet 4.6gpt-oss-120b
LMArena Vision1283—
Blueprint-Bench 26.7%—
LMArena Document1482—

Multilingual Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 54.4 (#41), gpt-oss-120b: 48.0 (#147)

BenchmarkClaude Sonnet 4.6gpt-oss-120b
LMArena Non-English14401351
LMArena Chinese14911385
LMArena French14651369
LMArena German14281353
LMArena Japanese14201331
LMArena Korean14111282
LMArena Russian14401343
LMArena Spanish14641389

Instruction Following Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 77.4 (#25), gpt-oss-120b: 69.3 (#173)

BenchmarkClaude Sonnet 4.6gpt-oss-120b
LMArena Instruction Following14751318
IFEval—83.6%

Long Context Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 45.3 (#44), gpt-oss-120b: 31.4 (#278)

BenchmarkClaude Sonnet 4.6gpt-oss-120b
LMArena Longer Query14791319
Fiction.LiveBench—44.4%

Writing & Preference Claude Sonnet 4.6 leads

Claude Sonnet 4.6: 70.2 (#22), gpt-oss-120b: 46.5 (#217)

BenchmarkClaude Sonnet 4.6gpt-oss-120b
LMArena Text14581365
LMArena Creative Writing14351275
EQ-Bench Creative Writing1810961
LMArena Multi-Turn14641340
Short-Story Creative Writing—77.1%
WildBench—84.5%
EQ-Bench 41207—

Frequently asked questions

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

Claude Sonnet 4.6 is the stronger model overall, scoring 50.3 to 36.3 on the Noometry Index. gpt-oss-120b costs 85× less per token, which makes it the better buy when Claude Sonnet 4.6's lead doesn't matter for your workload.

Which is cheaper, Claude Sonnet 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 Sonnet 4.6 lists at $3 and $15.

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

Claude Sonnet 4.6 scores higher on coding benchmarks: 46.3 versus 33.5 in the Noometry coding category.

Which has the bigger context window?

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

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

33 benchmarks have published results for both models. Claude Sonnet 4.6 has 57 scored results on Noometry and gpt-oss-120b has 48.

Related comparisons

Go deeper