modelbenchmark.io

GPT-5.1

OpenAI · gpt-5-1

Compare

Sharper GPT-5 generation for coding, product work, and tool-assisted tasks

Specification

openai listing

Context
400K
Max output
128K
Released
2025-11-13
Knowledge cutoff
2024-09-30
Retires
2027-05-15
Open weights
no
Input
text, image
Output
text

Price

US dollars per million tokens · openai list price

Input
$1.25
Output
$10.00
Cache read
$0.125
Cache write
$1.25

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Batch inputopenai$0.625
Batch outputopenai$5.00
Priority inputazure$2.50
Priority outputazure$20.00

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

Quality

8 benchmarks · 2 sources

Composite
75th
percentile of 334 scored models
Rank
85 / 334
±0.06 sd
Evidence
8 × 2
3 or more benchmarks, from 2 or more sources
Effort range
8.3
points between effort settings
coding61st1/3 bench
reasoning77th3/4 bench
math73rd3/7 bench
knowledge65th1/1 bench

By reasoning effort

every setting placed on the same scale as the leaderboard

SettingCompositeBenchmarks behind it
high84th7
medium71st6
low57th4

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
GPQA diamond87.6 ±1.9highEpoch AI2025-11-13
85.0 ±2.1mediumEpoch AI2025-11-17
Settings differ by 2.6 points on this benchmark.
OTIS Mock AIME 2024-202588.6 ±4.0highEpoch AI2025-11-13
85.6 ±4.4mediumEpoch AI2025-11-17
63.9 ±5.9lowEpoch AI2025-11-25
Settings differ by 24.7 points on this benchmark.
SWE-Bench verified66.9 ±2.1high · 2 runsEpoch AI2026-02-18
66.0medium · mini-SWE-agentSWE-bench
Sources and settings disagree by 0.9 points. Both figures stand.
Chess Puzzles32.0 ±4.7highEpoch AI2025-12-08
14.0 ±3.5lowEpoch AI2026-08-07
Settings differ by 18.0 points on this benchmark.
SimpleQA Verified48.0 ±1.6highEpoch AI2026-08-27
FrontierMath-v131.0 ±2.7highEpoch AI2025-11-13
26.9 ±2.6mediumEpoch AI2025-11-17
17.3 ±2.2lowEpoch AI2025-11-25
Settings differ by 13.7 points on this benchmark.
FrontierMath-Tier-4-2025-07-0112.5 ±4.8highEpoch AI2025-11-13
4.2 ±2.9mediumEpoch AI2025-11-17
Settings differ by 8.3 points on this benchmark.
Mystery Game Puzzles19.0 ±3.9lowEpoch AI2026-08-27
16.0 ±3.7mediumEpoch AI2026-08-27
Settings differ by 3.0 points on this benchmark.

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

Available from 32 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
openaivendor$1.25$10.00$0.125
400K
272K
128K
opencode$1.07$8.50$0.107400K128K
poe$1.10$9.00$0.11400K128K
jiekou$1.125$9.00400K128K
302ai$1.25$10.00400K128K
abacus$1.25$10.00$0.125400K128K
aihubmix$1.25$10.00$0.13400K128K
azure
$1.25
$1.38
$1.7188
$10.00
$11.00
$13.75
$0.125
$0.14
$0.1719
400K
272K
128K2027-05-15
azure-cognitive-services$1.25$10.00$0.125400K128K
cloudflare-ai-gateway$1.25$10.00$0.125128K128K
databricks$1.25$10.00$0.125$1.25
400K
272K
128K
edenai$1.25$10.00$0.125400K128K
gmi · gmi$1.25$10.00410K32K
helicone$1.25$10.00$0.125400K128K
impossibl$1.25$10.00$0.125400K128K
kilo$1.25$10.00$0.125400K128K
llmgateway$1.25$10.00$0.125400K128K
llmgateway-providers$1.25$10.00$0.125400K128K
merge-gateway$1.25$10.00$0.125400K128K
nano-gpt$1.25$10.00$0.125400K128K
nearai$1.25$10.00$0.125400K128K
neon$1.25$10.00$0.125400K128K
ofox$1.25$10.00$0.13400K128K
openrouter$1.25$10.00$0.125
400K
272K
128K
orcarouter$1.25$10.00$0.125400K128K
perplexity$1.25$10.00$0.125
perplexity-agent$1.25$10.00$0.125400K128K
pioneer$1.25$10.00$0.125$1.25400K131K
zenmux$1.25$10.00$0.12400K64K
cortecs$1.375$10.96$0.156400K128K
anyapi400K128K
github_copilot · github-copilot128K64K

Price history

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

DateHostField$/M
2026-09-02azureCache read$0.125
2026-09-04azureCache read$0.125
2026-09-02openrouterCache read$0.125
2026-09-06openrouterCache read$0.125
2026-09-02azureInput$1.25
2026-09-04azureInput$1.25
2026-09-02openrouterInput$1.25
2026-09-06openrouterInput$1.25
2026-09-02azureOutput$10.00
2026-09-04azureOutput$10.00
2026-09-02openrouterOutput$10.00
2026-09-06openrouterOutput$10.00

More from OpenAI

most-hosted first