ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

Claude 3.7 SonnetvsGPT-5.5

GPT-5.5 leads 2 of 2 shared benchmarks. Claude 3.7 Sonnet is 1.9x cheaper per token. GPT-5.5 has the larger context window (1M tokens).

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

Shared benchmarks
0 – 2
GPT-5.5 leads
Cheaper per token
Claude 3.7 Sonnet
1.9x cheaper, input + output
Larger context
GPT-5.5
1M tokens
Provider uptime (30d)
100% · 94.2446%
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-5.5
OpenAI · released 2026-04-23
textvision
Context
1M
Max out
128K
Input /1M
$5
Output /1M
$30
Cached /1M
$0.5
Scores
21 · 10 core
Quality

Benchmark matrix

BenchmarkClaude 3.7 SonnetGPT-5.5ΔEdge
Reported by both · 2
GPQA Diamond79.7% epoch90.7% epoch-11 ptGPT-5.5
OTIS Mock AIME 2024-2025 (Epoch AI run)57.8% epoch84.4% epoch-26.6 ptGPT-5.5
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-5.5 reports · 19
AIME 2026not reported100% matharena
LMArena Elonot reported1465.6
ARC-AGI-1 (Verified)not reported95%
ARC-AGI-2 (Verified)not reported85%
BrowseCompnot reported84.4%
FrontierMath Tier 1-3not reported51.7%
FrontierMath Tier 4not reported35.4%
FrontierMath Tier 4 v2 (Epoch AI run)not reported72.5% epoch
FrontierMath Tiers 1-3 v2 (Epoch AI run)not reported85.3% epoch
GDPval (wins or ties)not reported84.9%
MCP Atlasnot reported75.3%
MMMU-Pro (no tools)not reported81.2%
MMMU-Pro (with tools)not reported83.2%
OSWorld-Verifiednot reported78.7%
SimpleQA Verifiednot reported63% epoch
SWE-Bench Pronot reported58.6%
Tau2-bench Telecomnot reported98%
Terminal-Bench 2.0not reported82.7%
Toolathlonnot reported55.6%
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-5.5 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-5.5Edge
Context window200K tokens1M tokensGPT-5.5
Max output128K tokens128K tokensTie
Input price / 1M$3 $5 Claude 3.7 Sonnet
Output price / 1M$15 $30 Claude 3.7 Sonnet
Cached input / 1M$0.3 $0.5 Claude 3.7 Sonnet
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$18$35Claude 3.7 Sonnet
Modalitiestext · visiontext · visionTie
Released2025-02-242026-04-23
Cited benchmark scores521
Reliability

Provider status

All providers
More matchups

Claude 3.7 Sonnet vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run Claude 3.7 Sonnet and GPT-5.5 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.