Compare / head-to-head
gpt-oss-120bvsQwen3.8-Flash-Next
Qwen3.8-Flash-Next leads 1 of 1 shared benchmark. Qwen3.8-Flash-Next has the larger context window (1M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0 – 1
Qwen3.8-Flash-Next leads
Cheaper per token
—
list price, input + output
Larger context
Qwen3.8-Flash-Next
1M tokens
Provider uptime (30d)
94.2446% · —
OpenAI · Qwen
gpt-oss-120b
OpenAI · released 2025-08-05
text
- Context
- 131K
- Max out
- 131K
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 6 · 5 core
textvision
- Context
- 1M
- Max out
- —
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 13 · 4 core
Quality
Benchmark matrix
1 shared · 4 only gpt-oss-120b · 12 only Qwen3.8-Flash-Next| Benchmark | gpt-oss-120b | Qwen3.8-Flash-Next | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 1 | ||||
| GPQA Diamond | 80.1% ↗ | 91.7% ↗ | -11.6 pt | Qwen3.8-Flash-Next |
| Only gpt-oss-120b reports · 4 | ||||
| SWE-bench Verified | 62.4% ↗ | not reported | — | — |
| AIME 2025 | 90% ↗matharena ⚠ | not reported | — | — |
| LMArena Elo | 1365.9 ↗ | not reported | — | — |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 88.9% ↗epoch | not reported | — | — |
| Only Qwen3.8-Flash-Next reports · 12 | ||||
| Agents' Last Exam Pass@1 | not reported | 24.3% ↗ | — | — |
| Agents' Last Exam Score | not reported | 51.2 ↗ | — | — |
| CoWorkBench | not reported | 73.9% ↗ | — | — |
| DeepSWE 1.1 | not reported | 58.7% ↗ | — | — |
| Humanity's Last Exam | not reported | 35.9% ↗ | — | — |
| IFBench | not reported | 81.3% ↗ | — | — |
| JobBench | not reported | 55.7% ↗ | — | — |
| LiveCodeBench v6 | not reported | 91.9% ↗ | — | — |
| NL2Repo-Bench | not reported | 48.1% ↗ | — | — |
| SWE-bench Multilingual | not reported | 81% ↗ | — | — |
| SWE-bench Pro | not reported | 62.5% ↗ | — | — |
| Toolathlon Verified | not reported | 73.5% ↗ | — | — |
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 Qwen3.8-Flash-Next 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
Official pricing pages and model cards| Spec | gpt-oss-120b | Qwen3.8-Flash-Next | Edge |
|---|---|---|---|
| Context window | 131K tokens | 1M tokens | Qwen3.8-Flash-Next |
| Max output | 131K tokens | — | — |
| Input price / 1M | — | — | — |
| Output price / 1M | — | — | — |
| Cached input / 1M | — | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | — | — | — |
| Modalities | text | text · vision | Qwen3.8-Flash-Next |
| Released | 2025-08-05 | — | — |
| Cited benchmark scores | 6 | 13 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
gpt-oss-120b vs …
Models sharing the most benchmarksMore matchups
Qwen3.8-Flash-Next vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run gpt-oss-120b and Qwen3.8-Flash-Next on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.