ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Claude 3.5 SonnetvsGPT-5 Pro

GPT-5 Pro leads 1 of 1 shared benchmark. Claude 3.5 Sonnet is 7.5x cheaper per token. GPT-5 Pro has the larger context window (400K tokens).

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

Shared benchmarks
0 – 1
GPT-5 Pro leads
Cheaper per token
Claude 3.5 Sonnet
7.5x cheaper, input + output
Larger context
GPT-5 Pro
400K tokens
Provider uptime (30d)
100% · 95.3353%
Anthropic · OpenAI
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
GPT-5 Pro
OpenAI · released 2025-10-06
textvision
Context
400K
Max out
272K
Input /1M
$15
Output /1M
$120
Cached /1M
Scores
3 · 3 core
Quality

Benchmark matrix

BenchmarkClaude 3.5 SonnetGPT-5 ProΔEdge
Reported by both · 1
GPQA Diamond55.3% epoch88.4% -33.1 ptGPT-5 Pro
Only Claude 3.5 Sonnet reports · 3
SWE-bench Verified49% not reported
AIME 20253.3% matharenanot reported
OTIS Mock AIME 2024-2025 (Epoch AI run)8.5% epochnot reported
Only GPT-5 Pro reports · 2
FrontierMath Tier 4 v2 (Epoch AI run)not reported19.5% epoch
FrontierMath Tiers 1-3 v2 (Epoch AI run)not reported55.8% 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 3.5 Sonnet minus GPT-5 Pro 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 SonnetGPT-5 ProEdge
Context window200K tokens400K tokensGPT-5 Pro
Max output8K tokens272K tokensGPT-5 Pro
Input price / 1M$3 $15 Claude 3.5 Sonnet
Output price / 1M$15 $120 Claude 3.5 Sonnet
Cached input / 1M$0.3
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$18$135Claude 3.5 Sonnet
Modalitiestext · visiontext · visionTie
Released2024-10-222025-10-06
Cited benchmark scores43
Reliability

Provider status

All providers
More matchups

Claude 3.5 Sonnet vs …

More matchups

GPT-5 Pro vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Claude 3.5 Sonnet and GPT-5 Pro on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.