Noometry

Model comparison

GPT-4.1 mini vs Mistral Medium 3.5

Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 33.6 on the Noometry Index. GPT-4.1 mini costs 4.3× less per token, which makes it the better buy when Mistral Medium 3.5's lead doesn't matter for your workload.

Last verified . 19 shared benchmarks.

GPT-4.1 mini OpenAI

33.6

Rank #240 Confirmed

Mistral Medium 3.5 Mistral AI

40.2

Rank #152 Confirmed

Summary

  • They share 19 benchmarks with published results for both. GPT-4.1 mini scores higher in 0 categories and Mistral Medium 3.5 in 9 categories; 8 gaps are clear of the uncertainty.
  • The widest gap is in math, where Mistral Medium 3.5 leads 39.1 to 24.1.
  • The biggest single-benchmark swing is Kagi LLM Benchmark: 48.6% for GPT-4.1 mini and 41.4% for Mistral Medium 3.5.
  • GPT-4.1 mini is cheaper at $0.40 / $1.60 per million input/output tokens, against $1.50 / $7.50 for Mistral Medium 3.5.
  • GPT-4.1 mini accepts more context: 1.05M tokens versus 262K.
  • Mistral Medium 3.5 has downloadable open weights; the other is API-only.

Side by side

GPT-4.1 miniMistral Medium 3.5
ProviderOpenAIMistral AI
Noometry Index33.640.2
Released2025-04-14—
WeightsProprietaryOpen
Context window1.05M262K
Max output33K210K
Input $ / M tokens$0.40$1.50
Output $ / M tokens$1.60$7.50
Results tracked4722

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

Category by category

Coding Mistral Medium 3.5 leads

GPT-4.1 mini: 30.6 (#293), Mistral Medium 3.5: 36.0 (#213)

BenchmarkGPT-4.1 miniMistral Medium 3.5
LMArena Coding13671461
SWE-bench Verified (bash only)23.9%—
Aider Polyglot32.4%—
LMArena WebDev—1264
SciCode40.4%—
WeirdML37.6%—
BigCodeBench Instruct48.9%—
CadEval16%—

Agentic & Tool Use Not comparable

GPT-4.1 mini: 33.3 (#55), Mistral Medium 3.5: —

BenchmarkGPT-4.1 miniMistral Medium 3.5
Berkeley Function Calling Leaderboard50.5%—

Reasoning Mistral Medium 3.5 leads

GPT-4.1 mini: 10.8 (#340), Mistral Medium 3.5: 17.3 (#295)

BenchmarkGPT-4.1 miniMistral Medium 3.5
Kagi LLM Benchmark48.6%41.4%
LMArena Hard Prompts13491436
Epoch Capabilities Index135.01141.35
ARC-AGI-20%—
NYT Connections (extended)—12.9%
ARC-AGI-13.5%—
CritPt0%—
Chess Puzzles7%—
Mystery Game Puzzles7%—
DTBench68.8%—
LMCA21.1%—

Math Mistral Medium 3.5 leads

GPT-4.1 mini: 24.1 (#270), Mistral Medium 3.5: 39.1 (#113)

BenchmarkGPT-4.1 miniMistral Medium 3.5
LMArena Math13431431
FrontierMath (Tiers 1-3)6.7%—
OTIS Mock AIME 2024-202544.7%—
Omni-MATH49.1%—
MATH Level 587.3%—
FrontierMath (Feb 2025 set)4.5%—

Knowledge Mistral Medium 3.5 leads

GPT-4.1 mini: 34.7 (#194), Mistral Medium 3.5: 40.0 (#126)

BenchmarkGPT-4.1 miniMistral Medium 3.5
LMArena Expert13381432
GPQA Diamond65.8%—
SimpleQA Verified12.7%—
MMLU-Pro78.3%—
GPQA (HELM)61.4%—

Multimodal Mistral Medium 3.5 leads

GPT-4.1 mini: 35.8 (#82), Mistral Medium 3.5: 38.3 (#65)

BenchmarkGPT-4.1 miniMistral Medium 3.5
LMArena Vision11811223

Multilingual Mistral Medium 3.5 leads

GPT-4.1 mini: 45.7 (#166), Mistral Medium 3.5: 51.9 (#100)

BenchmarkGPT-4.1 miniMistral Medium 3.5
LMArena Non-English13181404
LMArena Chinese13291442
LMArena French13581448
LMArena German13511451
LMArena Korean12981385
LMArena Russian13241395
LMArena Spanish13191409
LMArena Japanese1290—

Instruction Following Too close to call

GPT-4.1 mini: 73.7 (#118), Mistral Medium 3.5: 74.6 (#90)

BenchmarkGPT-4.1 miniMistral Medium 3.5
LMArena Instruction Following13331415
IFEval90.4%—

Long Context Mistral Medium 3.5 leads

GPT-4.1 mini: 31.8 (#275), Mistral Medium 3.5: 43.2 (#103)

BenchmarkGPT-4.1 miniMistral Medium 3.5
LMArena Longer Query13441415
Fiction.LiveBench44.4%—

Writing & Preference Mistral Medium 3.5 leads

GPT-4.1 mini: 48.6 (#199), Mistral Medium 3.5: 58.5 (#117)

BenchmarkGPT-4.1 miniMistral Medium 3.5
LMArena Text13401421
LMArena Creative Writing13001374
LMArena Multi-Turn13541423
EQ-Bench Creative Writing1147—
WildBench83.8%—
EQ-Bench 4—993

Frequently asked questions

Is GPT-4.1 mini better than Mistral Medium 3.5?

Mistral Medium 3.5 is the stronger model overall, scoring 40.2 to 33.6 on the Noometry Index. GPT-4.1 mini costs 4.3× less per token, which makes it the better buy when Mistral Medium 3.5's lead doesn't matter for your workload.

Which is cheaper, GPT-4.1 mini or Mistral Medium 3.5?

GPT-4.1 mini is cheaper. It lists at $0.40 per million input tokens and $1.60 per million output tokens; Mistral Medium 3.5 lists at $1.50 and $7.50.

Is GPT-4.1 mini or Mistral Medium 3.5 better for coding?

Mistral Medium 3.5 scores higher on coding benchmarks: 36.0 versus 30.6 in the Noometry coding category.

Which has the bigger context window?

GPT-4.1 mini does, with 1.05M tokens against 262K.

How many benchmarks do GPT-4.1 mini and Mistral Medium 3.5 share?

19 benchmarks have published results for both models. GPT-4.1 mini has 47 scored results on Noometry and Mistral Medium 3.5 has 22.

Related comparisons

Go deeper