Noometry

Model comparison

Claude 2 vs GPT-5 Mini

GPT-5 Mini is the stronger model overall, scoring 41.8 to 25.0 on the Noometry Index.

Last verified . 5 shared benchmarks.

Claude 2 Anthropic

25.0

Rank #346 Reported

GPT-5 Mini OpenAI

41.8

Rank #128 Confirmed

Summary

  • They share 5 benchmarks with published results for both. Claude 2 scores higher in 0 categories and GPT-5 Mini in 3 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in math, where GPT-5 Mini leads 46.7 to 9.3.
  • The biggest single-benchmark swing is MATH Level 5: 11.7% for Claude 2 and 97.8% for GPT-5 Mini.

Side by side

Claude 2GPT-5 Mini
ProviderAnthropicOpenAI
Noometry Index25.041.8
Released2023-07-112025-08-07
WeightsProprietaryProprietary
Context window—400K
Max output—128K
Input $ / M tokens—$0.25
Output $ / M tokens—$2
Results tracked860

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

Category by category

Coding Not comparable

Claude 2: —, GPT-5 Mini: 40.1 (#146)

BenchmarkClaude 2GPT-5 Mini
SWE-bench Verified—64.7%
SWE-bench Verified (bash only)—59.8%
SWE-bench Multilingual—39.7%
SciCode—39.2%
WeirdML—52.7%
LMArena Coding—1406
ALE-Bench—799.77
AlgoTune—1.38
HumanEval+61.6%—

Agentic & Tool Use Not comparable

Claude 2: —, GPT-5 Mini: 31.1 (#70)

BenchmarkClaude 2GPT-5 Mini
Terminal-Bench—34.8%
Berkeley Function Calling Leaderboard—55.5%
Vending-Bench 2—-31.18

Reasoning GPT-5 Mini leads

Claude 2: 21.7 (#216), GPT-5 Mini: 23.9 (#168)

BenchmarkClaude 2GPT-5 Mini
DTBench51.9%80.5%
Epoch Capabilities Index120.13145.52
ARC-AGI-2—4.4%
Kagi LLM Benchmark—70.3%
ARC-AGI-1—54.3%
CritPt—0%
Chess Puzzles—30%
EnigmaEval—8.2%
LMArena Hard Prompts—1380
Mystery Game Puzzles—10%
LMCA—34.2%
ForecastBench—61

Math GPT-5 Mini leads

Claude 2: 9.3 (#320), GPT-5 Mini: 46.7 (#69)

BenchmarkClaude 2GPT-5 Mini
OTIS Mock AIME 2024-20252.5%86.7%
MATH Level 511.7%97.8%
FrontierMath (Tiers 1-3)—46.7%
FrontierMath Tier 4—12.2%
ProofBench—9%
Omni-MATH—72.2%
LMArena Math—1378
FrontierMath (Feb 2025 set)—27.2%
FrontierMath Tier 4 (v1)—6.3%

Knowledge GPT-5 Mini leads

Claude 2: 16.9 (#287), GPT-5 Mini: 45.6 (#86)

BenchmarkClaude 2GPT-5 Mini
GPQA Diamond34.7%75%
Humanity's Last Exam—19.4%
SimpleQA Verified—21.6%
MMLU-Pro—83.5%
Confabulations—13.3%
Vectara Hallucination Rate—12.9%
GPQA (HELM)—75.6%
LMArena Expert—1379
MMLU78.5%—
TriviaQA87.5%—

Multimodal Not comparable

Claude 2: —, GPT-5 Mini: 35.6 (#85)

BenchmarkClaude 2GPT-5 Mini
LMArena Vision—1202
VPCT—40.2%

Multilingual Not comparable

Claude 2: —, GPT-5 Mini: 48.9 (#137)

BenchmarkClaude 2GPT-5 Mini
LMArena Non-English—1363
LMArena Chinese—1385
LMArena French—1386
LMArena German—1366
LMArena Japanese—1341
LMArena Korean—1308
LMArena Russian—1362
LMArena Spanish—1355

Instruction Following Not comparable

Claude 2: —, GPT-5 Mini: 76.2 (#46)

BenchmarkClaude 2GPT-5 Mini
IFEval—92.7%
LMArena Instruction Following—1357

Long Context Not comparable

Claude 2: —, GPT-5 Mini: 41.9 (#132)

BenchmarkClaude 2GPT-5 Mini
Fiction.LiveBench—69.4%
LMArena Longer Query—1355

Writing & Preference Not comparable

Claude 2: —, GPT-5 Mini: 55.2 (#148)

BenchmarkClaude 2GPT-5 Mini
LMArena Text—1373
LMArena Creative Writing—1325
Short-Story Creative Writing—83.1%
EQ-Bench Creative Writing—1313
WildBench—85.5%
LMArena Multi-Turn—1363

Frequently asked questions

Is Claude 2 better than GPT-5 Mini?

GPT-5 Mini is the stronger model overall, scoring 41.8 to 25.0 on the Noometry Index.

How many benchmarks do Claude 2 and GPT-5 Mini share?

5 benchmarks have published results for both models. Claude 2 has 8 scored results on Noometry and GPT-5 Mini has 60.

Related comparisons

Go deeper