ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

GPT-5 minivsMinistral 3 3B

GPT-5 mini leads 2 of 2 shared benchmarks. Ministral 3 3B is 11.3x cheaper per token. GPT-5 mini has the larger context window (400K tokens).

Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.

Shared benchmarks
2 – 0
GPT-5 mini leads
Cheaper per token
Ministral 3 3B
11.3x cheaper, input + output
Larger context
GPT-5 mini
400K tokens
Provider uptime (30d)
95.2381% · 100%
OpenAI · Mistral AI
GPT-5 mini
OpenAI · released 2025-08-07
textvision
Context
400K
Max out
128K
Input /1M
$0.25
Output /1M
$2
Cached /1M
$0.025
Scores
9 · 8 core
Ministral 3 3B
Mistral AI · released 2025-12-02
textvision
Context
256K
Max out
Input /1M
$0.1
Output /1M
$0.1
Cached /1M
$0.01
Scores
3 · 2 core
Quality

Benchmark matrix

BenchmarkGPT-5 miniMinistral 3 3BΔEdge
Reported by both · 2
GPQA Diamond81.6% 53.4% +28.2 ptGPT-5 mini
AIME 202587.5% matharena72.1% +15.4 ptGPT-5 mini
Only GPT-5 mini reports · 6
SWE-bench Verified71% not reported
FrontierMath Tier 4 v2 (Epoch AI run)12.2% epochnot reported
FrontierMath Tiers 1-3 v2 (Epoch AI run)46.7% epochnot reported
OTIS Mock AIME 2024-2025 (Epoch AI run)86.7% epochnot reported
SimpleQA Verified21.6% epochnot reported
SWE-bench Verified (Epoch AI run)64.7% epochnot reported
Only Ministral 3 3B reports · 1
LiveCodeBenchnot reported54.8%
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is GPT-5 mini minus Ministral 3 3B in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing

Side by side

SpecGPT-5 miniMinistral 3 3BEdge
Context window400K tokens256K tokensGPT-5 mini
Max output128K tokens
Input price / 1M$0.25 $0.1 Ministral 3 3B
Output price / 1M$2 $0.1 Ministral 3 3B
Cached input / 1M$0.025 $0.01 Ministral 3 3B
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$2.25$0.2Ministral 3 3B
Modalitiestext · visiontext · visionTie
Released2025-08-072025-12-02
Cited benchmark scores93
Reliability

Provider status

All providers
Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run GPT-5 mini and Ministral 3 3B on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.