Compare · ModelsLive · 2 picked · head to head
GPT-4.1 Nano vs Mistral Small 3.1 24B
Side by side · benchmarks, pricing, and signals you can act on.
Winner summary
GPT-4.1 Nano wins on 7/9 benchmarks
GPT-4.1 Nano wins 7 of 9 shared benchmarks. Leads in knowledge · language · math.
Category leads
general·Mistral Small 3.1 24Bknowledge·GPT-4.1 Nanolanguage·GPT-4.1 Nanomath·GPT-4.1 Nanoreasoning·GPT-4.1 Nano
Hype vs Reality
Attention vs performance
GPT-4.1 Nano
#246 by perf·no signal
Mistral Small 3.1 24B
#194 by perf·no signal
Best value
GPT-4.1 Nano
1.4x better value than Mistral Small 3.1 24B
GPT-4.1 Nano
124.0 pts/$
$0.25/M
Mistral Small 3.1 24B
86.5 pts/$
$0.45/M
Vendor risk
Who is behind the model
OpenAI
$840.0B·Tier 1
Mistral AI
$14.0B·Tier 1
Head to head
9 benchmarks · 2 models
GPT-4.1 NanoMistral Small 3.1 24B
Dtbench
Mistral Small 3.1 24B leads by +10.2
GPT-4.1 Nano
20.9
Mistral Small 3.1 24B
31.1
GPQA diamond
GPT-4.1 Nano leads by +1.9
Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs.
GPT-4.1 Nano
31.9
Mistral Small 3.1 24B
30.0
HELM · GPQA
GPT-4.1 Nano leads by +11.5
GPT-4.1 Nano
50.7
Mistral Small 3.1 24B
39.2
HELM · IFEval
GPT-4.1 Nano leads by +9.3
GPT-4.1 Nano
84.3
Mistral Small 3.1 24B
75.0
HELM · MMLU-Pro
Mistral Small 3.1 24B leads by +6.0
GPT-4.1 Nano
55.0
Mistral Small 3.1 24B
61.0
HELM · Omni-MATH
GPT-4.1 Nano leads by +11.9
GPT-4.1 Nano
36.7
Mistral Small 3.1 24B
24.8
HELM · WildBench
GPT-4.1 Nano leads by +2.3
GPT-4.1 Nano
81.1
Mistral Small 3.1 24B
78.8
MATH level 5
GPT-4.1 Nano leads by +23.2
MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics.
GPT-4.1 Nano
70.0
Mistral Small 3.1 24B
46.8
OTIS Mock AIME 2024-2025
GPT-4.1 Nano leads by +23.1
OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills.
GPT-4.1 Nano
28.8
Mistral Small 3.1 24B
5.7
Full benchmark table
| Benchmark | GPT-4.1 Nano | Mistral Small 3.1 24B |
|---|---|---|
Dtbench | 20.9 | 31.1 |
GPQA diamond Graduate-Level Google-Proof QA (Diamond set) · expert-crafted questions in physics, biology, and chemistry that are difficult even for domain PhDs. | 31.9 | 30.0 |
HELM · GPQA | 50.7 | 39.2 |
HELM · IFEval | 84.3 | 75.0 |
HELM · MMLU-Pro | 55.0 | 61.0 |
HELM · Omni-MATH | 36.7 | 24.8 |
HELM · WildBench | 81.1 | 78.8 |
MATH level 5 MATH Level 5 · the hardest tier of the MATH benchmark, featuring competition-level problems from AMC, AIME, and Olympiad-style mathematics. | 70.0 | 46.8 |
OTIS Mock AIME 2024-2025 OTIS Mock AIME 2024-2025 · simulated American Invitational Mathematics Examination problems testing advanced problem-solving skills. | 28.8 | 5.7 |
Pricing · per 1M tokens · projected $/mo at 10M tokens
| Model | Input | Output | Context | Projected $/mo |
|---|---|---|---|---|
| $0.10 | $0.40 | 1.0M tokens (~524 books) | $1.75 | |
| $0.35 | $0.56 | 128K tokens (~64 books) | $4.02 |
People also compared