ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

GPT-5.5vsGPT-5.6 Luna

GPT-5.5 and GPT-5.6 Luna split their 6 shared benchmarks evenly. GPT-5.6 Luna is 25x cheaper per token. GPT-5.6 Luna has the larger context window (1.1M tokens).

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

Shared benchmarks
3 – 3
even split
Cheaper per token
GPT-5.6 Luna
25x cheaper, input + output
Larger context
GPT-5.6 Luna
1.1M tokens
Provider uptime (30d)
95.3216%
OpenAI
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
GPT-5.6 Luna
OpenAI · released 2026-07-09
textvision
Context
1.1M
Max out
128K
Input /1M
$0.2
Output /1M
$1.2
Cached /1M
$0.02
Scores
8 · 6 core
Quality

Benchmark matrix

BenchmarkGPT-5.5GPT-5.6 LunaΔEdge
Reported by both · 6
GPQA Diamond90.7% epoch92.3% -1.6 ptGPT-5.6 Luna
FrontierMath Tier 4 v2 (Epoch AI run)72.5% epoch61% epoch+11.5 ptGPT-5.5
FrontierMath Tiers 1-3 v2 (Epoch AI run)85.3% epoch82.1% epoch+3.2 ptGPT-5.5
OTIS Mock AIME 2024-2025 (Epoch AI run)84.4% epoch98.3% epoch-13.9 ptGPT-5.6 Luna
SimpleQA Verified63% epoch41% epoch+22 ptGPT-5.5
SWE-Bench Pro58.6% 62.7% -4.1 ptGPT-5.6 Luna
Only GPT-5.5 reports · 15
AIME 2026100% matharenanot reported
LMArena Elo1465.6 not reported
ARC-AGI-1 (Verified)95% not reported
ARC-AGI-2 (Verified)85% not reported
BrowseComp84.4% not reported
FrontierMath Tier 1-351.7% not reported
FrontierMath Tier 435.4% not reported
GDPval (wins or ties)84.9% not reported
MCP Atlas75.3% not reported
MMMU-Pro (no tools)81.2% not reported
MMMU-Pro (with tools)83.2% not reported
OSWorld-Verified78.7% not reported
Tau2-bench Telecom98% not reported
Terminal-Bench 2.082.7% not reported
Toolathlon55.6% not reported
Only GPT-5.6 Luna reports · 1
DeepSWE v1.1not reported67.2%
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 GPT-5.5 minus GPT-5.6 Luna 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

SpecGPT-5.5GPT-5.6 LunaEdge
Context window1M tokens1.1M tokensGPT-5.6 Luna
Max output128K tokens128K tokensTie
Input price / 1M$5 $0.2 GPT-5.6 Luna
Output price / 1M$30 $1.2 GPT-5.6 Luna
Cached input / 1M$0.5 $0.02 GPT-5.6 Luna
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$35$1.4GPT-5.6 Luna
Modalitiestext · visiontext · visionTie
Released2026-04-232026-07-09
Cited benchmark scores218
Reliability

OpenAI status

All providers
More matchups

GPT-5.6 Luna vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run GPT-5.5 and GPT-5.6 Luna on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.