The Known Good Updated 25 Jul 2026
OpenAI: GPT-5 Nano vs OpenAI: gpt-oss-120b ·OpenAI vs OpenAI

OpenAI: GPT-5 Nano vs OpenAI: gpt-oss-120b — head-to-head comparison

OpenAI: GPT-5 Nano profile OpenAI: gpt-oss-120b profile All comparisons
OpenAI: GPT-5 Nano — OpenAI
Quality
#37 of 61
57based on 3 of 6 evaluations
Known Good Index
Speed
#28 of 316
121.4
Output tokens per second
Price
#56 of 340
$0.14
Blended per 1M tokens
In $0.05 · Out $0.40
Cache hit price
#13 of 206
$0.005
per 1M tokens (−90%)
Context
#105 of 345
400k
tokens (~600 pages)
OpenAI: gpt-oss-120b — OpenAI
Quality
#33 of 61
61based on 3 of 6 evaluations
Known Good Index
Speed
#9 of 316
172.8
Output tokens per second
Price
#33 of 340
$0.07
Blended per 1M tokens
In $0.04 · Out $0.17
Cache hit price
#25 of 206
$0.015
per 1M tokens (−59%)
Context
#238 of 345
131k
tokens (~200 pages)
Summary

On the Known Good Index, OpenAI: GPT-5 Nano scores 57 and OpenAI: gpt-oss-120b scores 61 — a 4-point lead for OpenAI: gpt-oss-120b. They share 3 published evaluations, with OpenAI: GPT-5 Nano ahead on 1 and OpenAI: gpt-oss-120b ahead on 2.

Blended pricing is $0.14 per 1M tokens for OpenAI: GPT-5 Nano and $0.07 for OpenAI: gpt-oss-120b — OpenAI: gpt-oss-120b is about 2.0× cheaper.

Throughput is 121 tokens per second for OpenAI: GPT-5 Nano and 173 for OpenAI: gpt-oss-120b, with time to first token at 2.9s and 0.7s. OpenAI: GPT-5 Nano accepts 400k tokens of context against 131k.

OpenAI: GPT-5 Nano is proprietary; OpenAI: gpt-oss-120b is open weights under Open weights (unrestricted). 19 tracked hosts serve one or both.

Generated from tracked data on 26 Jul 2026 · how these comparisons are computed →

At a glance
MetricOpenAI: GPT-5 NanoOpenAI: gpt-oss-120b
Known Good Index 57 based on 3 of 6 evaluations 61 based on 3 of 6 evaluations
Blended $/1M $0.14 $0.07
Output tok/s 121 173
Context window 400k 131k
Providers 2 17
Jump to section

Quality

Known Good Index and the capability indices, side by side

IndicesComponents
Index scores

Each index is min-max normalised across tracked models and scaled 0–100 from published evaluations. We do not run these evaluations.

MetricOpenAI: GPT-5 NanoOpenAI: gpt-oss-120b
Known Good Index 57 61
Mathematics Index 89 89
Science Index 69 77
Agentic Index 21 18
Openness Index 5 60
The Known Good

Quality Breakdown

Every evaluation both models report a published score for

Evaluations both models report

Bar = OpenAI: GPT-5 Nano · marker = OpenAI: gpt-oss-120b · scores ingested from Epoch AI (CC-BY 4.0)

GPQA Diamond69 / 76
MATH / AIME81 / 89
Terminal-Bench22 / 19

Right-hand figures read OpenAI: GPT-5 Nano / OpenAI: gpt-oss-120b. OpenAI: GPT-5 Nano leads on 1 of 3, OpenAI: gpt-oss-120b on 2.

The Known Good

Arena Elo

Human preference rating from blind pairwise votes

Arena ratings

Elo from blind pairwise votes, ingested from Arena. Higher is better.

MetricOpenAI: GPT-5 NanoOpenAI: gpt-oss-120b
Text Arena 1,366
Text Arena (style controlled) 1,352
The Known Good

Price & Cost

Published API pricing by token type

Per token typeCache discount
Published pricing

USD per 1M tokens. Blended is a 3:1 input:output mix. Live from OpenRouter, cross-checked against models.dev. Lower is better.

MetricOpenAI: GPT-5 NanoOpenAI: gpt-oss-120b
Input $/1M $0.05 $0.04
Output $/1M $0.40 $0.17
Blended $/1M $0.14 $0.07
Cache read $/1M $0.005 $0.015
The Known Good
We publish blended price rather than cost-per-task. Cost-per-task requires token counts from an evaluation suite we do not run. Blended price is computed from published rates and is fully reproducible — see the pricing methodology.

Context Window

Maximum input accepted and maximum output emitted

Context and output limits

Provider-declared limits, from metadata via models.dev and OpenRouter. Higher is better.

MetricOpenAI: GPT-5 NanoOpenAI: gpt-oss-120b
Context window 400k 131k
Max output tokens 128k 131k
The Known Good

Speed & Latency

Median throughput and time to first token across hosting providers

Output speedTime to first token
Throughput and latency

Medians across all tracked providers, derived from OpenRouter endpoint telemetry.

MetricOpenAI: GPT-5 NanoOpenAI: gpt-oss-120b
Output tokens/s 121 173
Time to first token 2.9s 0.7s
The Known Good

Providers

Which hosts serve each model, and at what price and speed

19 hosts
Full provider benchmarks →
Provider OpenAI: GPT-5 Nano blendedOpenAI: GPT-5 Nano tok/s OpenAI: gpt-oss-120b blendedOpenAI: gpt-oss-120b tok/s
OpenAI · first party $0.07 205
Azure · first party $0.14 63
Cerebras $0.45 505
Groq $0.26 445
SambaNova $0.34 304
DeepInfra $0.07 282
BaseTen $0.20 255
Nebius $0.26 255
Mara $0.30 198
Parasail $0.26 198
Google · first party $0.16 197
Together $0.26 108
Amazon Bedrock · first party $0.26 103
Phala $0.26 86
Novita $0.10 67
DigitalOcean $0.17 63
Mancer 2 $0.17 49
SiliconFlow $0.15 29
CoreWeave $0.07 24

Per-host pricing and telemetry from OpenRouter. A dash means that host does not serve that model.

The Known Good
Sources for this page
Pricing & providers — OpenRouter Metadata — models.dev Benchmarks — Epoch AI (CC-BY 4.0)Elo — Arena Full attribution →