modelbenchmark.io

GPT-5.5

OpenAI · gpt-5-5

Compare

Default frontier GPT for coding, computer use, research, and knowledge work

Specification

openai listing

Context
1.1M
Max output
128K
Released
2026-04-23
Knowledge cutoff
2025-12-01
Retires
2027-10-26
Open weights
no
Input
text, image, pdf
Output
text

Price

US dollars per million tokens · openai list price

Input
$5.00
Output
$30.00
Cache read
$0.50
Cache write
$5.00

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Batch inputopenai$2.50
Batch outputopenai$15.00
Priority inputazure_ai$10.00
Priority inputazure$13.75
Priority inputopenai$12.50
Priority outputazure_ai$60.00
Priority outputazure$82.50
Priority outputopenai$75.00

Batch input is 50% below the interactive input price at the same listing.

Long-context price tiers

the rate above each context threshold

AbovePrice$/M
272KCache read$1.00
272KInput$10.00
272KOutput$45.00

Quality

16 benchmarks · 2 sources

Composite
93rd
percentile of 334 scored models
Rank
23 / 334
±0.06 sd
Evidence
16 × 2
3 or more benchmarks, from 2 or more sources
Effort range
21.8
points between effort settings
coding47th2/3 bench
reasoning96th4/4 bench
math94th6/7 bench
knowledge86th1/1 bench
general89th1/1 bench

By reasoning effort

every setting placed on the same scale as the leaderboard

SettingCompositeBenchmarks behind it
xhigh97th6
low88th4
high85th2
medium41st1

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
Mystery Game Puzzles56.0 ±5.0xhighEpoch AI2026-07-24
52.0 ±5.0highEpoch AI2026-07-27
28.0 ±4.5lowEpoch AI2026-08-28
Settings differ by 28.0 points on this benchmark.
FrontierMath-Tier-4-2025-07-0135.4 ±6.9defaultEpoch AI2026-04-23
FrontierMath-Tiers-1-3-v285.3 ±2.1xhighEpoch AI2026-06-11
Chess Puzzles54.0 ±5.0defaultEpoch AI2026-04-24
26.0 ±4.4lowEpoch AI2026-08-07
Settings differ by 28.0 points on this benchmark.
FrontierMath-Tier-4-v272.5 ±7.2xhighEpoch AI2026-06-11
FrontierMath-v151.7 ±2.9defaultEpoch AI2026-04-23
SimpleQA Verified63.0 ±1.5xhighEpoch AI2026-08-27
GPQA diamond94.0 ±1.5defaultEpoch AI2026-04-24
90.7 ±1.8lowEpoch AI2026-05-05
Settings differ by 3.3 points on this benchmark.
SWE-Bench verified80.6 ±1.8defaultEpoch AI2026-04-24
OTIS Mock AIME 2024-2025100.0 ±0.0defaultEpoch AI2026-04-24
84.4 ±5.5lowEpoch AI2026-08-07
Settings differ by 15.6 points on this benchmark.
LiveBench80.8xhigh · 23 runsLiveBench2026-06-25
EBR-bench34.3 ±2.0xhighEpoch AI2026-07-27
OEIS Open Lite36.0 ±4.8mediumEpoch AI2026-08-11
FrontierMath-Erdos0.0 ±0.0xhighEpoch AI2026-08-28
MirrorCode10.0 ±6.0highEpoch AI2026-08-10
OEIS Open26.2 ±2.0mediumEpoch AI2026-08-11

The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.

Available from 49 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
openaivendor$5.00$30.00$0.501.1M128K
kenarifreefree1.1M128K
unorouter · freefreefree1.1M128K
unorouter$0.1875$1.1251.1M128K
xpersona$1.50$12.00$0.151.1M128K
frogbot$2.50$15.00$0.25272K128K
poe$4.5455$27.2727$0.4545400K128K
302ai$5.00$30.001.1M128K
abacus$5.00$30.00$0.501M128K
ai-router$5.00$30.00$0.501.1M128K
aihubmix$5.00$30.00$0.501.1M128K
azure
$5.00
$5.50
$30.00
$33.00
$0.50
$0.55
1.1M128K2027-10-26
azure_ai$5.00$30.00$0.501.1M128K2027-10-26
azure-cognitive-services$5.00$30.00$0.501.1M128K
cloudflare-ai-gateway$5.00$30.001M128K
crossmodel$5.00$30.00$0.50$5.001.1M128K
daoxe$5.00$30.00$0.501.1M128K
databricks$5.00$30.00$0.50$5.00
1.1M
922K
128K
edenai$5.00$30.00$0.501.1M128K
fastrouter$5.00$30.001.1M128K
freemodel$5.00$30.00$0.50$5.001.1M128K
github-copilot$5.00$30.00$0.501.1M128K
gmicloud$5.00$30.00$0.501.1M128K
hpc-ai$5.00$30.00$0.501.1M128K
impossibl$5.00$30.00$0.501.1M128K
kilo$5.00$30.00$0.501.1M128K
llmgateway$5.00$30.00$0.501.1M128K
llmgateway-providers$5.00$30.00$0.501.1M128K
merge-gateway$5.00$30.00$0.501.1M128K
nano-gpt$5.00$30.00$0.501.1M128K
nearai$5.00$30.00$0.501.1M128K
neon$5.00$30.00$0.501.1M128K
ofox$5.00$30.00$0.501.1M128K
opencode$5.00$30.00$0.501.1M128K
openrouter$5.00$30.00$0.501.1M128K
opper$5.00$30.00$0.501.1M128K
orcarouter$5.00$30.00$0.501.1M128K
perplexity$5.00$30.00$0.50
perplexity-agent$5.00$30.00$0.501.1M128K
pioneer$5.00$30.00$0.50$5.001.1M128K
sap-ai-core$5.00$30.00$0.501.1M128K
vercel$5.00$30.00$0.501M128K
vivgrid$5.00$30.00$0.501.1M128K
zenmux$5.00$30.00$0.501.1M128K
amazon-bedrock$5.50$33.00$0.55272K128K
bedrock_mantle · bedrock-mantle$5.50$33.00$0.551.1M128K
requesty$5.50$33.00$0.551.1M128K
chatgpt · chatgpt1.1M128K
model-oracle-ai1.1M128K

Price history

append-only observations · a listing writes a row only when its price moves

DateHostField$/M
2026-09-02databricksCache read$0.50
2026-09-06databricksCache read$0.50
2026-09-02openrouterCache read$0.50
2026-09-06openrouterCache read$0.50
2026-09-02databricksInput$5.00
2026-09-06databricksInput$5.00
2026-09-02openrouterInput$5.00
2026-09-06openrouterInput$5.00
2026-09-02databricksOutput$30.00
2026-09-06databricksOutput$30.00
2026-09-02openrouterOutput$30.00
2026-09-06openrouterOutput$30.00

Other listings of this model

same model, different key

More from OpenAI

most-hosted first