ModelsCompareBest forBenchmarksStatusPricingAPI
Compare / head-to-head

gpt-oss-120bvso3-pro

gpt-oss-120b and o3-pro do not yet share a public benchmark, so quality cannot be compared apples-to-apples. o3-pro has the larger context window (200K tokens).

Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.

Shared benchmarks
0
no overlap yet
Cheaper per token
list price, input + output
Larger context
o3-pro
200K tokens
Provider uptime (30d)
94.4444%
OpenAI
gpt-oss-120b
OpenAI · released 2025-08-05
text
Context
131K
Max out
131K
Input /1M
Output /1M
Cached /1M
Scores
6 · 5 core
o3-pro
OpenAI · released 2025-06-10
textvision
Context
200K
Max out
100K
Input /1M
$20
Output /1M
$80
Cached /1M
Scores
0 · 0 core
Quality

Benchmark matrix

Benchmarkgpt-oss-120bo3-proΔEdge
Reported by both · 0
No public benchmark is reported for both models yet.
Only gpt-oss-120b reports · 5
SWE-bench Verified62.4% not reported
GPQA Diamond80.1% not reported
AIME 202590% matharenanot reported
LMArena Elo1365.9 not reported
OTIS Mock AIME 2024-2025 (Epoch AI run)88.9% epochnot reported
Only o3-pro reports · 0
o3-pro reports nothing gpt-oss-120b does not.
Scores tagged "epoch" or "matharena" are independent runs, used only where the lab has not published its own; ⚠ marks rows MathArena flags as released after the competition. Higher is better on every row. Δ is gpt-oss-120b minus o3-pro in the benchmark's own unit. "Not reported" means the lab has not published that figure; it is not a zero. ↗ opens the source.
Specs & pricing

Side by side

Specgpt-oss-120bo3-proEdge
Context window131K tokens200K tokenso3-pro
Max output131K tokens100K tokensgpt-oss-120b
Input price / 1M$20
Output price / 1M$80
Cached input / 1M
Input + output / 1M
Lower is cheaper. List prices; batch, tool and regional fees excluded.
$100
Modalitiestexttext · visiono3-pro
Released2025-08-052025-06-10
Cited benchmark scores60
Reliability

OpenAI status

All providers
More matchups

gpt-oss-120b vs …

Built by Respan
Which one wins on your data?

Public benchmarks are a starting point. Run gpt-oss-120b and o3-pro on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.