ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Claude 3.7 SonnetvsGPT-4.1 mini

Claude 3.7 Sonnet leads 2 of 2 shared benchmarks. GPT-4.1 mini is 9x cheaper per token. GPT-4.1 mini has the larger context window (1.0M tokens).

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

Shared benchmarks
2 – 0
Claude 3.7 Sonnet leads
Cheaper per token
GPT-4.1 mini
9x cheaper, input + output
Larger context
GPT-4.1 mini
1.0M tokens
Provider uptime (30d)
100% · 94.8052%
Anthropic · OpenAI
Claude 3.7 Sonnet
Anthropic · released 2025-02-24
textvision
Context
200K
Max out
128K
Input /1M
$3
Output /1M
$15
Cached /1M
$0.3
Scores
5 · 5 core
GPT-4.1 mini
OpenAI · released 2025-04-14
textvision
Context
1.0M
Max out
33K
Input /1M
$0.4
Output /1M
$1.6
Cached /1M
$0.1
Scores
7 · 6 core
Quality

Benchmark matrix

BenchmarkClaude 3.7 SonnetGPT-4.1 miniΔEdge
Reported by both · 2
GPQA Diamond79.7% epoch65% +14.7 ptClaude 3.7 Sonnet
OTIS Mock AIME 2024-2025 (Epoch AI run)57.8% epoch44.7% epoch+13.1 ptClaude 3.7 Sonnet
Only Claude 3.7 Sonnet reports · 3
SWE-bench Verified70.3% not reported
AIME 202549.2% matharenanot reported
SWE-bench Verified (Epoch AI run)61% epochnot reported
Only GPT-4.1 mini reports · 4
MMLUnot reported87.5%
AIME 2024not reported49.6%
FrontierMath Tiers 1-3 v2 (Epoch AI run)not reported6.7% epoch
SimpleQA Verifiednot reported12.7% epoch
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 3.7 Sonnet minus GPT-4.1 mini 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 3.7 SonnetGPT-4.1 miniEdge
Context window200K tokens1.0M tokensGPT-4.1 mini
Max output128K tokens33K tokensClaude 3.7 Sonnet
Input price / 1M$3 $0.4 GPT-4.1 mini
Output price / 1M$15 $1.6 GPT-4.1 mini
Cached input / 1M$0.3 $0.1 GPT-4.1 mini
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$18$2GPT-4.1 mini
Modalitiestext · visiontext · visionTie
Released2025-02-242025-04-14
Cited benchmark scores57
Reliability

Provider status

All providers
More matchups

Claude 3.7 Sonnet vs …

More matchups

GPT-4.1 mini vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Claude 3.7 Sonnet and GPT-4.1 mini on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.