OpenAI, released Jul 18, 2024

GPT-4o miniprice, context, benchmarks and release details

100% confidence, 4 of 6 expected sources in

22.9

SI Score

#142 of 142 ranked models

Input, per 1M tokens: $0.15
Output, per 1M tokens: $0.60
Context window: 128K
Max output: 16.4K
Released: Jul 18, 2024

How the score breaks down

Coding 3.6

Math 22.7

Preference 60.6

Reasoning 7.5

Weights: reasoning 30%, math 15%, coding 40%, preference 15%. Results use fixed 0–100 scales before averaging, and thin evidence is pulled toward 50. Method si-v3-retained-evidence-2, computed Oct 9, 2026, 05:13 UTC.

Around it on the leaderboard

138 Llama-3.2-1B 32.1
139 GPT-4.1 nano 32.1
140 GPT-4o 31.2
141 Llama 4 Maverick 17B Instruct 30.0
142 GPT-4o mini 22.9

Full leaderboard

Benchmark results

8 benchmarks, 8 results

Each row shows the best published result. Where a model was tested at several settings, such as reasoning effort, open the row to see each one. Hover or tap a value for its source.

ARC-AGI-2 (public eval)reasoning 0% 0.0

ARC-AGI-2 (semi-private)reasoning 0% 0.0

GPQA Diamondreasoning 37.7% 37.7

FrontierMath Tiers 1–3 (v2)math 0.7% 0.7

MATH Level 5math 52.6% 52.6

OTIS Mock AIME 2024–2025math 6.9% 6.9

Aider Polyglotcoding 3.6% 3.6

LMArena Textpreference 1286.4 elo 60.6

Normalization uses a fixed 0–100 scale for each unit, independent of other models. Compare evaluation conditions before reading a small gap as decisive. “Lab-reported” marks the provider's own published figure.

Details and sources

Open weights: No
License: not yet reported
Input modalities: text, image, pdf
First seen by SuperIndex: Oct 8, 2026
Coverage: 80% of expected source weight

Reported (4)

Aider polyglotOct 8, 2026
ARC PrizeOct 8, 2026
Epoch AI BenchmarkingOct 8, 2026
LMArena / ArenaOct 8, 2026

Awaiting (2)

Official model cards via models.dev5% of weight
LiveBench15% of weight

Confidence rises as pending sources publish. Some sources never cover some models, so confidence reaches 100% at 80% of expected weight.