ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Claude 3.5 SonnetvsMinistral 3 3B

Claude 3.5 Sonnet and Ministral 3 3B split their 2 shared benchmarks evenly. Ministral 3 3B is 90x cheaper per token. Ministral 3 3B has the larger context window (256K tokens).

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

Shared benchmarks
1 – 1
even split
Cheaper per token
Ministral 3 3B
90x cheaper, input + output
Larger context
Ministral 3 3B
256K tokens
Provider uptime (30d)
100% · 100%
Anthropic · Mistral AI
Claude 3.5 Sonnet
Anthropic · released 2024-10-22
textvision
Context
200K
Max out
8K
Input /1M
$3
Output /1M
$15
Cached /1M
$0.3
Scores
4 · 4 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

BenchmarkClaude 3.5 SonnetMinistral 3 3BΔEdge
Reported by both · 2
GPQA Diamond55.3% epoch53.4% +1.9 ptClaude 3.5 Sonnet
AIME 20253.3% matharena72.1% -68.8 ptMinistral 3 3B
Only Claude 3.5 Sonnet reports · 2
SWE-bench Verified49% not reported
OTIS Mock AIME 2024-2025 (Epoch AI run)8.5% 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 Claude 3.5 Sonnet 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

SpecClaude 3.5 SonnetMinistral 3 3BEdge
Context window200K tokens256K tokensMinistral 3 3B
Max output8K tokens
Input price / 1M$3 $0.1 Ministral 3 3B
Output price / 1M$15 $0.1 Ministral 3 3B
Cached input / 1M$0.3 $0.01 Ministral 3 3B
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$18$0.2Ministral 3 3B
Modalitiestext · visiontext · visionTie
Released2024-10-222025-12-02
Cited benchmark scores43
Reliability

Provider status

All providers
More matchups

Claude 3.5 Sonnet vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Claude 3.5 Sonnet and Ministral 3 3B on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.