Noometry

Model comparison

GPT-5.4 mini vs Pixtral Large

GPT-5.4 mini is the stronger model overall, scoring 44.8 to 31.7 on the Noometry Index.

Last verified . 2 shared benchmarks.

GPT-5.4 mini OpenAI

44.8

Rank #69 Confirmed

Pixtral Large Mistral AI

31.7

Rank #257 Reported

Summary

  • They share 2 benchmarks with published results for both. GPT-5.4 mini scores higher in 3 categories and Pixtral Large in 0 categories; 3 gaps are clear of the uncertainty.
  • The widest gap is in writing & preference, where GPT-5.4 mini leads 64.2 to 32.9.
  • GPT-5.4 mini is cheaper at $0.75 / $4.50 per million input/output tokens, against $2 / $6 for Pixtral Large.
  • GPT-5.4 mini accepts more context: 400K tokens versus 128K.
  • Pixtral Large has downloadable open weights; the other is API-only.

Side by side

GPT-5.4 miniPixtral Large
ProviderOpenAIMistral AI
Noometry Index44.831.7
Released2026-03-172024-11-01
WeightsProprietaryOpen
Context window400K128K
Max output128K128K
Input $ / M tokens$0.75$2
Output $ / M tokens$4.50$6
Results tracked463

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

Category by category

Coding Not comparable

GPT-5.4 mini: 45.0 (#67), Pixtral Large: —

BenchmarkGPT-5.4 miniPixtral Large
FrontierCode27%—
LMArena WebDev1397—
SciCode49.9%—
WeirdML60.3%—
LMArena Coding1438—
ALE-Bench1,189—

Agentic & Tool Use Not comparable

GPT-5.4 mini: 29.6 (#74), Pixtral Large: —

BenchmarkGPT-5.4 miniPixtral Large
DeepResearch Bench36.3%—

Reasoning GPT-5.4 mini leads

GPT-5.4 mini: 30.3 (#77), Pixtral Large: 20.9 (#208)

BenchmarkGPT-5.4 miniPixtral Large
ARC-AGI-218.9%—
Kagi LLM Benchmark37.9%—
NYT Connections (extended)61.8%—
ARC-AGI-163.7%—
CritPt10%—
Chess Puzzles24%—
EnigmaEval—0.8%
Thematic Generalization61.7%—
LMArena Hard Prompts1424—
Mystery Game Puzzles11%—
DTBench80%—
LMCA40.8%—
Epoch Capabilities Index148.83—
ForecastBench57—

Math Not comparable

GPT-5.4 mini: 45.4 (#63), Pixtral Large: —

BenchmarkGPT-5.4 miniPixtral Large
FrontierMath (Tiers 1-3)51.2%—
FrontierMath Tier 49.8%—
OTIS Mock AIME 2024-202588.9%—
ProofBench21%—
LMArena Math1418—
FrontierMath (Feb 2025 set)28.3%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge Not comparable

GPT-5.4 mini: 51.4 (#62), Pixtral Large: —

BenchmarkGPT-5.4 miniPixtral Large
GPQA Diamond86.9%—
SimpleQA Verified29.4%—
Vectara Hallucination Rate5.5%—
LMArena Expert1434—

Multimodal GPT-5.4 mini leads

GPT-5.4 mini: 39.0 (#51), Pixtral Large: 30.0 (#105)

BenchmarkGPT-5.4 miniPixtral Large
LMArena Vision12451089

Multilingual Not comparable

GPT-5.4 mini: 52.1 (#94), Pixtral Large: —

BenchmarkGPT-5.4 miniPixtral Large
LMArena Non-English1405—
LMArena Chinese1446—
LMArena French1440—
LMArena German1407—
LMArena Japanese1375—
LMArena Korean1369—
LMArena Russian1417—
LMArena Spanish1403—

Instruction Following Not comparable

GPT-5.4 mini: 74.3 (#99), Pixtral Large: —

BenchmarkGPT-5.4 miniPixtral Large
LMArena Instruction Following1405—

Long Context Not comparable

GPT-5.4 mini: 42.9 (#107), Pixtral Large: —

BenchmarkGPT-5.4 miniPixtral Large
LMArena Longer Query1407—

Writing & Preference GPT-5.4 mini leads

GPT-5.4 mini: 64.2 (#56), Pixtral Large: 32.9 (#273)

BenchmarkGPT-5.4 miniPixtral Large
EQ-Bench Creative Writing1665988
LMArena Text1411—
LMArena Creative Writing1370—
LMArena Multi-Turn1429—

Frequently asked questions

Is GPT-5.4 mini better than Pixtral Large?

GPT-5.4 mini is the stronger model overall, scoring 44.8 to 31.7 on the Noometry Index.

Which is cheaper, GPT-5.4 mini or Pixtral Large?

GPT-5.4 mini is cheaper. It lists at $0.75 per million input tokens and $4.50 per million output tokens; Pixtral Large lists at $2 and $6.

Which has the bigger context window?

GPT-5.4 mini does, with 400K tokens against 128K.

How many benchmarks do GPT-5.4 mini and Pixtral Large share?

2 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Pixtral Large has 3.

Related comparisons

Go deeper