ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Claude Sonnet 4.5vsGPT-5 mini

Claude Sonnet 4.5 and GPT-5 mini split their 8 shared benchmarks evenly. GPT-5 mini is 8x 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
4 – 4
even split
Cheaper per token
GPT-5 mini
8x cheaper, input + output
Larger context
GPT-5 mini
400K tokens
Provider uptime (30d)
100% · 95.5182%
Anthropic · OpenAI
Claude Sonnet 4.5
Anthropic · released 2025-09-29
textvision
Context
200K
Max out
64K
Input /1M
$3
Output /1M
$15
Cached /1M
$0.3
Scores
21 · 10 core
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
Quality

Benchmark matrix

BenchmarkClaude Sonnet 4.5GPT-5 miniΔEdge
Reported by both · 8
SWE-bench Verified77.2% 71% +6.2 ptClaude Sonnet 4.5
GPQA Diamond83.4% 81.6% +1.8 ptClaude Sonnet 4.5
AIME 202584.2% matharena87.5% matharena-3.3 ptGPT-5 mini
FrontierMath Tier 4 v2 (Epoch AI run)2.4% epoch12.2% epoch-9.8 ptGPT-5 mini
FrontierMath Tiers 1-3 v2 (Epoch AI run)23.9% epoch46.7% epoch-22.8 ptGPT-5 mini
OTIS Mock AIME 2024-2025 (Epoch AI run)77.8% epoch86.7% epoch-8.9 ptGPT-5 mini
SimpleQA Verified30.7% epoch21.6% epoch+9.1 ptClaude Sonnet 4.5
SWE-bench Verified (Epoch AI run)71.3% epoch64.7% epoch+6.6 ptClaude Sonnet 4.5
Only Claude Sonnet 4.5 reports · 12
Humanity's Last Exam (no tools)17.7% not reported
ARC-AGI-2 (Verified)13.6% not reported
GDPval-AA1276 not reported
Humanity's Last Exam (with tools)33.6% not reported
MCP Atlas43.8% not reported
MMMLU89.5% not reported
MMMU-Pro (no tools)63.4% not reported
MMMU-Pro (with tools)68.9% not reported
OSWorld-Verified61.4% not reported
Tau2-bench Retail86.2% not reported
Tau2-bench Telecom98% not reported
Terminal-Bench 2.051% not reported
Only GPT-5 mini reports · 0
GPT-5 mini reports nothing Claude Sonnet 4.5 does not.
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 Sonnet 4.5 minus GPT-5 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 Sonnet 4.5GPT-5 miniEdge
Context window200K tokens400K tokensGPT-5 mini
Max output64K tokens128K tokensGPT-5 mini
Input price / 1M$3 $0.25 GPT-5 mini
Output price / 1M$15 $2 GPT-5 mini
Cached input / 1M$0.3 $0.025 GPT-5 mini
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$18$2.25GPT-5 mini
Modalitiestext · visiontext · visionTie
Released2025-09-292025-08-07
Cited benchmark scores219
Reliability

Provider status

All providers
More matchups

Claude Sonnet 4.5 vs …

More matchups

GPT-5 mini vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Claude Sonnet 4.5 and GPT-5 mini on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.