Noometry

Model comparison

GPT-5.4 mini vs Magistral Medium

GPT-5.4 mini is the stronger model overall, scoring 45.0 to 35.2 on the Noometry Index.

Last verified . 22 shared benchmarks.

GPT-5.4 mini OpenAI

45.0

Rank #76 Confirmed

Magistral Medium Mistral AI

35.2

Rank #227 Confirmed

Summary

  • They share 22 benchmarks with published results for both. GPT-5.4 mini scores higher in 8 categories and Magistral Medium in 0 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in reasoning, where GPT-5.4 mini leads 30.4 to 8.6.
  • The biggest single-benchmark swing is ARC-AGI-1: 63.7% for GPT-5.4 mini and 6.1% for Magistral Medium.
  • GPT-5.4 mini is cheaper at $0.75 / $4.50 per million input/output tokens, against $2 / $5 for Magistral Medium.
  • GPT-5.4 mini accepts more context: 400K tokens versus 262K.
  • Magistral Medium has downloadable open weights; the other is API-only.

Side by side

GPT-5.4 miniMagistral Medium
ProviderOpenAIMistral AI
Noometry Index45.035.2
Released2026-03-172025-03-17
WeightsProprietaryOpen
Context window400K262K
Max output128K16K
Input $ / M tokens$0.75$2
Output $ / M tokens$4.50$5
Results tracked4622

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

Category by category

Coding GPT-5.4 mini leads

GPT-5.4 mini: 45.2 (#72), Magistral Medium: 39.1 (#161)

BenchmarkGPT-5.4 miniMagistral Medium
SciCode49.9%39.2%
LMArena Coding14381319
FrontierCode27%—
LMArena WebDev1397—
WeirdML60.3%—
ALE-Bench1,189—

Agentic & Tool Use Not comparable

GPT-5.4 mini: 29.9 (#81), Magistral Medium: —

BenchmarkGPT-5.4 miniMagistral Medium
DeepResearch Bench36.3%—

Reasoning GPT-5.4 mini leads

GPT-5.4 mini: 30.4 (#85), Magistral Medium: 8.6 (#348)

BenchmarkGPT-5.4 miniMagistral Medium
ARC-AGI-218.9%0%
Kagi LLM Benchmark37.9%16.2%
ARC-AGI-163.7%6.1%
CritPt10%0.3%
LMArena Hard Prompts14241267
NYT Connections (extended)61.8%—
Chess Puzzles24%—
Thematic Generalization61.7%—
Mystery Game Puzzles11%—
DTBench80%—
LMCA40.8%—
Epoch Capabilities Index148.84—
ForecastBench57—

Math GPT-5.4 mini leads

GPT-5.4 mini: 45.5 (#75), Magistral Medium: 35.1 (#189)

BenchmarkGPT-5.4 miniMagistral Medium
LMArena Math14191250
FrontierMath (Tiers 1-3)51.2%—
FrontierMath Tier 49.8%—
OTIS Mock AIME 2024-202588.9%—
ProofBench21%—
FrontierMath (Feb 2025 set)28.3%—
FrontierMath Tier 4 (v1)2.1%—

Knowledge GPT-5.4 mini leads

GPT-5.4 mini: 51.5 (#67), Magistral Medium: 33.5 (#202)

BenchmarkGPT-5.4 miniMagistral Medium
LMArena Expert14351223
GPQA Diamond86.9%—
SimpleQA Verified29.4%—
Vectara Hallucination Rate5.5%—

Multimodal Not comparable

GPT-5.4 mini: 39.7 (#56), Magistral Medium: —

BenchmarkGPT-5.4 miniMagistral Medium
LMArena Vision1245—

Multilingual GPT-5.4 mini leads

GPT-5.4 mini: 51.9 (#96), Magistral Medium: 39.6 (#224)

BenchmarkGPT-5.4 miniMagistral Medium
LMArena Non-English14051232
LMArena Chinese14461227
LMArena French14401267
LMArena German14091248
LMArena Japanese13741175
LMArena Korean13681125
LMArena Russian14171224
LMArena Spanish14051271

Instruction Following GPT-5.4 mini leads

GPT-5.4 mini: 74.1 (#102), Magistral Medium: 66.0 (#211)

BenchmarkGPT-5.4 miniMagistral Medium
LMArena Instruction Following14051254

Long Context GPT-5.4 mini leads

GPT-5.4 mini: 43.0 (#112), Magistral Medium: 39.3 (#183)

BenchmarkGPT-5.4 miniMagistral Medium
LMArena Longer Query14071295

Writing & Preference GPT-5.4 mini leads

GPT-5.4 mini: 64.0 (#58), Magistral Medium: 46.3 (#219)

BenchmarkGPT-5.4 miniMagistral Medium
LMArena Text14121255
LMArena Creative Writing13701245
LMArena Multi-Turn14291275
EQ-Bench Creative Writing1665—

Frequently asked questions

Is GPT-5.4 mini better than Magistral Medium?

GPT-5.4 mini is the stronger model overall, scoring 45.0 to 35.2 on the Noometry Index.

Which is cheaper, GPT-5.4 mini or Magistral Medium?

GPT-5.4 mini is cheaper. It lists at $0.75 per million input tokens and $4.50 per million output tokens; Magistral Medium lists at $2 and $5.

Is GPT-5.4 mini or Magistral Medium better for coding?

GPT-5.4 mini scores higher on coding benchmarks: 45.2 versus 39.1 in the Noometry coding category.

Which has the bigger context window?

GPT-5.4 mini does, with 400K tokens against 262K.

How many benchmarks do GPT-5.4 mini and Magistral Medium share?

22 benchmarks have published results for both models. GPT-5.4 mini has 46 scored results on Noometry and Magistral Medium has 22.

Related comparisons

Go deeper