MDL
o4-mini
OpenAI
Verified against Artificial Analysis · Jul 13, 2026
Capability
83
percentile index
Price /M
$1.1 / $4.4
in / out
Context
200K
tokens
Avg score
63.2
11 benchmarks
AA Intelligence
25.6
index
Speed
192 tok/s
TTFT 19s
Released
Apr 16, 2025
About
o4-mini is a proprietary model in the o4 family from OpenAI. Benchmarked on 11 evals, averaging 63.2.
Benchmark scores · 11
avg 63.2 — higher is betterThe research behind this model
all papers mentioning it →Reinforcement Learning for Tool-Calling Agents in Fast Healthcare Interoperability Resources (FHIR)May 13, 2026When Simulation Lies: A Sim-to-Real Benchmark and Domain-Randomized RL Recipe for Tool-Use AgentsMay 12, 2026
Mentions matched by name in title/abstract — from the arXiv + HF daily corpus.
Performance & price
Output speed192 tok/s
Latency (TTFT)19s
Price in / out$1.1 / $4.4 per 1M
Blended price$1.93 / 1M
Math index90.7
Median across API providers, via Artificial Analysis. Blended = 3:1 input:output. For reasoning models, latency includes thinking time. Methodology →
History
full ledger →Capability over time
Append-only ledger — every observed change to this model's numbers.
API providers
Artificial Analysis$4.4/M