modelbenchmark.io

GPT-5 Mini

OpenAI · gpt-5-mini

Compare

Small GPT-5 for responsive agents, coding help, and everyday automation

Specification

openai listing

Context
400K
Max output
128K
Released
2025-08-07
Knowledge cutoff
2024-05-30
Retires
2026-12-11
Open weights
no
Input
text, image
Output
text

Price

US dollars per million tokens · openai list price

Input
$0.25
Output
$2.00
Cache read
$0.025
Cache write
$0.25

Batch and priority prices

US dollars per million tokens · per listing

PriceListing$/M
Batch inputopenai$0.125
Batch outputopenai$1.00
Priority inputopenai$0.45
Priority outputopenai$3.60

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

Quality

11 benchmarks · 2 sources

Composite
54th
percentile of 334 scored models
Rank
153 / 334
±0.05 sd
Evidence
11 × 2
3 or more benchmarks, from 2 or more sources
Effort range
3.3
points between effort settings
coding48th1/3 bench
reasoning54th3/4 bench
math62nd6/7 bench
knowledge18th1/1 bench

By reasoning effort

every setting placed on the same scale as the leaderboard

SettingCompositeBenchmarks behind it
high61st10
medium57th9

Every score

one row per source and configuration — nothing averaged away

BenchmarkScoreConfigurationSourceRun
MATH level 597.8 ±0.3highEpoch AI2025-10-30
96.8 ±0.4mediumEpoch AI2025-08-20
Settings differ by 1.0 points on this benchmark.
OTIS Mock AIME 2024-202586.7 ±4.3highEpoch AI2025-10-30
66.9 ±7.5medium · 2 runsEpoch AI2026-08-07
Settings differ by 19.8 points on this benchmark.
GPQA diamond75.0 ±2.3highEpoch AI2025-10-30
71.7 ±3.2medium · 2 runsEpoch AI2026-08-07
Settings differ by 3.3 points on this benchmark.
FrontierMath-v130.2 ±2.4medium · 2 runsEpoch AI2025-11-13
28.6 ±2.6high · 2 runsEpoch AI2025-11-13
Settings differ by 1.6 points on this benchmark.
Chess Puzzles30.0 ±4.6highEpoch AI2026-08-07
9.5 ±2.6medium · 2 runsEpoch AI2026-08-07
Settings differ by 20.5 points on this benchmark.
SWE-Bench verified64.7 ±2.2mediumEpoch AI2026-02-01
59.8medium · mini-SWE-agentSWE-bench
56.2default · mini-SWE-agentSWE-bench
Sources and settings disagree by 8.5 points. Both figures stand.
FrontierMath-Tier-4-2025-07-013.1 ±0.0high · 2 runsEpoch AI2025-10-30
2.1 ±0.0medium · 2 runsEpoch AI2025-08-07
Settings differ by 1.0 points on this benchmark.
FrontierMath-Tiers-1-3-v246.7 ±3.0highEpoch AI2026-06-12
12.1 ±1.4medium · 2 runsEpoch AI2026-08-27
Settings differ by 34.6 points on this benchmark.
FrontierMath-Tier-4-v212.2 ±5.2highEpoch AI2026-06-12
SimpleQA Verified21.6 ±1.3highEpoch AI2026-08-10
Mystery Game Puzzles7.0 ±2.0medium · 2 runsEpoch AI2026-08-27
5.0 ±2.2highEpoch AI2026-08-27
Settings differ by 2.0 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 36 hosts

HostIn $/MOut $/MCache rdCache wrContextOutputRetires
openaivendor$0.25$2.00$0.025
400K
272K
128K2026-12-11
qihang-ai$0.04$0.29200K64K
poe$0.22$1.80$0.022400K128K
jiekou$0.225$1.80400K128K
302ai$0.25$2.00400K128K
abacus$0.25$2.00$0.025400K128K
azure
$0.25
$0.275
$2.00
$2.20
$0.03
$0.0275
$0.025
400K
272K
128K2027-02-09
azure-cognitive-services$0.25$2.00$0.03400K128K
cloudflare-ai-gateway$0.25$2.00$0.025128K128K
databricks$0.25$2.00$0.025$0.25
400K
272K
128K
edenai$0.25$2.00$0.025400K128K
fastrouter$0.25$2.00$0.025400K128K
github-copilot$0.25$2.00$0.025264K64K
helicone$0.25$2.00$0.025400K128K
impossibl$0.25$2.00$0.025400K128K
kilo$0.25$2.00$0.025400K128K
llmgateway$0.25$2.00$0.025400K128K
llmgateway-providers$0.25$2.00$0.025400K128K
merge-gateway$0.25$2.00$0.025400K128K
nano-gpt$0.25$2.00$0.025400K128K
nearai$0.25$2.00$0.025400K128K
neon$0.25$2.00$0.025400K128K
oci · oci$0.25$2.00272K128K
ofox$0.25$2.00$0.03256K33K
openrouter$0.25$2.00$0.025
400K
272K
128K
orcarouter$0.25$2.00$0.025400K128K
perplexity$0.25$2.00$0.025
perplexity-agent$0.25$2.00$0.025400K128K
pioneer$0.25$2.00$0.025$0.25400K128K
replicate · replicate$0.25$2.00
sap-ai-core$0.25$2.00$0.025400K128K
vercel$0.25$2.00$0.025400K128K
vivgrid$0.25$2.00$0.03272K128K
cortecs$0.279$2.192$0.056400K128K
anyapi400K128K
github_copilot · github-copilot128K64K

More from OpenAI

most-hosted first