Noometry

Model comparison

Claude Fable 5 vs gpt-oss-120b

Claude Fable 5 is the stronger model overall, scoring 66.8 to 36.3 on the Noometry Index. gpt-oss-120b costs 285× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.

Last verified . 34 shared benchmarks.

Claude Fable 5 Anthropic

66.8

Rank #5 Confirmed

gpt-oss-120b OpenAI

36.3

Rank #217 Confirmed

Summary

  • They share 34 benchmarks with published results for both. Claude Fable 5 scores higher in 9 categories and gpt-oss-120b in 0 categories; 9 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where Claude Fable 5 leads 76.8 to 20.0.
  • The biggest single-benchmark swing is Surface Evolver Bench: 95% for Claude Fable 5 and 25% for gpt-oss-120b.
  • gpt-oss-120b is cheaper at $0.037 / $0.17 per million input/output tokens, against $10 / $50 for Claude Fable 5.
  • Claude Fable 5 accepts more context: 1M tokens versus 131K.
  • gpt-oss-120b has downloadable open weights; the other is API-only.

Side by side

Claude Fable 5gpt-oss-120b
ProviderAnthropicOpenAI
Noometry Index66.836.3
Released2026-06-072025-08-05
WeightsProprietaryOpen
Context window1M131K
Max output128K41K
Input $ / M tokens$10$0.037
Output $ / M tokens$50$0.17
Results tracked6248

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

Category by category

Coding Claude Fable 5 leads

Claude Fable 5: 70.6 (#4), gpt-oss-120b: 33.5 (#256)

BenchmarkClaude Fable 5gpt-oss-120b
SciCode61%36%
WeirdML91.9%48.2%
LMArena Coding15191380
ALE-Bench2,041575.62
DeepSWE69.9%—
FrontierCode53.5%—
SWE-bench Verified (bash only)—26%
Aider Polyglot—41.8%
LMArena WebDev1625—
FrontierSWE47%—
GSO78.4%—
MirrorCode63.9%—
AlgoTune—1.41

Agentic & Tool Use Claude Fable 5 leads

Claude Fable 5: 54.0 (#2), gpt-oss-120b: 12.2 (#153)

BenchmarkClaude Fable 5gpt-oss-120b
APEX-Agents63.6%4.4%
Vending-Bench 25,680-21.53
Terminal-Bench—18.7%
Remote Labor Index16.1%—
τ²-bench Banking39.7%—
PostTrainBench41.8%—
GBAEval74.5%—
GDP.pdf30%—
LMArena Search1230—
METR Time Horizons—56.6%

Reasoning Claude Fable 5 leads

Claude Fable 5: 76.8 (#6), gpt-oss-120b: 20.0 (#245)

BenchmarkClaude Fable 5gpt-oss-120b
SimpleBench81.9%22.1%
Kagi LLM Benchmark91.4%58.6%
CritPt28.6%1.1%
Chess Puzzles41%20%
LMArena Hard Prompts15081364
Mystery Game Puzzles52%2%
DTBench98.4%76.3%
LMCA61.1%22.1%
Surface Evolver Bench95%25%
Epoch Capabilities Index162.06139.93
ARC-AGI-289.2%—
NYT Connections (extended)92.7%—
ARC-AGI-198.5%—
EnigmaEval39.3%—
EBR-Bench39.5%—
Bench to the Future 30.13—

Math Claude Fable 5 leads

Claude Fable 5: 88.5 (#5), gpt-oss-120b: 52.5 (#50)

BenchmarkClaude Fable 5gpt-oss-120b
OTIS Mock AIME 2024-2025100%88.9%
LMArena Math15191389
FrontierMath (Tiers 1-3)87%—
FrontierMath Tier 490.2%—
ProofBench95%—
Omni-MATH—68.8%
FrontierMath Erdős0%—

Knowledge Claude Fable 5 leads

Claude Fable 5: 62.2 (#25), gpt-oss-120b: 42.4 (#96)

BenchmarkClaude Fable 5gpt-oss-120b
GPQA Diamond85.9%75.8%
LMArena Expert15341356
SimpleQA Verified70.7%—
MMLU-Pro—79.5%
Confabulations—15.7%
Vectara Hallucination Rate—14.2%
GPQA (HELM)—68.4%

Multimodal Not comparable

Claude Fable 5: 45.3 (#17), gpt-oss-120b: —

BenchmarkClaude Fable 5gpt-oss-120b
LMArena Vision1324—
Blueprint-Bench 238.6%—
Furniture Assembly35.8%—
LMArena Document1496—

Multilingual Claude Fable 5 leads

Claude Fable 5: 57.3 (#9), gpt-oss-120b: 48.0 (#147)

BenchmarkClaude Fable 5gpt-oss-120b
LMArena Non-English14811351
LMArena Chinese15431385
LMArena French15051369
LMArena German14861353
LMArena Japanese15061331
LMArena Korean14881282
LMArena Russian15041343
LMArena Spanish14981389

Instruction Following Claude Fable 5 leads

Claude Fable 5: 78.6 (#8), gpt-oss-120b: 69.3 (#173)

BenchmarkClaude Fable 5gpt-oss-120b
LMArena Instruction Following15021318
IFEval—83.6%

Long Context Claude Fable 5 leads

Claude Fable 5: 46.3 (#23), gpt-oss-120b: 31.4 (#278)

BenchmarkClaude Fable 5gpt-oss-120b
LMArena Longer Query15091319
Fiction.LiveBench—44.4%

Writing & Preference Claude Fable 5 leads

Claude Fable 5: 75.9 (#5), gpt-oss-120b: 46.5 (#217)

BenchmarkClaude Fable 5gpt-oss-120b
LMArena Text14911365
LMArena Creative Writing14941275
EQ-Bench Creative Writing1943961
LMArena Multi-Turn15041340
Short-Story Creative Writing—77.1%
WildBench—84.5%
EQ-Bench 41340—

Frequently asked questions

Is Claude Fable 5 better than gpt-oss-120b?

Claude Fable 5 is the stronger model overall, scoring 66.8 to 36.3 on the Noometry Index. gpt-oss-120b costs 285× less per token, which makes it the better buy when Claude Fable 5's lead doesn't matter for your workload.

Which is cheaper, Claude Fable 5 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 Fable 5 lists at $10 and $50.

Is Claude Fable 5 or gpt-oss-120b better for coding?

Claude Fable 5 scores higher on coding benchmarks: 70.6 versus 33.5 in the Noometry coding category.

Which has the bigger context window?

Claude Fable 5 does, with 1M tokens against 131K.

How many benchmarks do Claude Fable 5 and gpt-oss-120b share?

34 benchmarks have published results for both models. Claude Fable 5 has 62 scored results on Noometry and gpt-oss-120b has 48.

Related comparisons

Go deeper