Compare / head-to-head
Claude Opus 4.8vsgpt-oss-120b
Claude Opus 4.8 leads 4 of 4 shared benchmarks. Claude Opus 4.8 has the larger context window (1M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
4 – 0
Claude Opus 4.8 leads
Cheaper per token
—
list price, input + output
Larger context
Claude Opus 4.8
1M tokens
Provider uptime (30d)
100% · 94.2446%
Anthropic · OpenAI
Claude Opus 4.8
Anthropic · released 2026-05-28
textvision
gpt-oss-120b
OpenAI · released 2025-08-05
text
- Context
- 131K
- Max out
- 131K
- Input /1M
- —
- Output /1M
- —
- Cached /1M
- —
- Scores
- 6 · 5 core
Quality
Benchmark matrix
4 shared · 12 only Claude Opus 4.8 · 1 only gpt-oss-120b| Benchmark | Claude Opus 4.8 | gpt-oss-120b | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 4 | ||||
| SWE-bench Verified | 88.6% ↗ | 62.4% ↗ | +26.2 pt | Claude Opus 4.8 |
| GPQA Diamond | 93.6% ↗ | 80.1% ↗ | +13.5 pt | Claude Opus 4.8 |
| LMArena Elo | 1452.7 ↗ | 1365.9 ↗ | +86.8 | Claude Opus 4.8 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 98.3% ↗epoch | 88.9% ↗epoch | +9.4 pt | Claude Opus 4.8 |
| Only Claude Opus 4.8 reports · 12 | ||||
| AIME 2026 | 100% ↗matharena ⚠ | not reported | — | — |
| Humanity's Last Exam (no tools) | 49.8% ↗ | not reported | — | — |
| BrowseComp | 84.3% ↗ | not reported | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | 56.1% ↗epoch | not reported | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 80% ↗epoch | not reported | — | — |
| Humanity's Last Exam (with tools) | 57.9% ↗ | not reported | — | — |
| OSWorld-Verified | 83.4% ↗ | not reported | — | — |
| SimpleQA Verified | 53% ↗epoch | not reported | — | — |
| SWE-bench Multilingual | 84.4% ↗ | not reported | — | — |
| SWE-bench Multimodal | 38.4% ↗ | not reported | — | — |
| SWE-Bench Pro | 69.2% ↗ | not reported | — | — |
| Terminal-Bench 2.1 | 74.6% ↗ | not reported | — | — |
| Only gpt-oss-120b reports · 1 | ||||
| AIME 2025 | not reported | 90% ↗matharena ⚠ | — | — |
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 Claude Opus 4.8 minus gpt-oss-120b 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 | Claude Opus 4.8 | gpt-oss-120b | Edge |
|---|---|---|---|
| Context window | 1M tokens | 131K tokens | Claude Opus 4.8 |
| Max output | 128K tokens | 131K tokens | gpt-oss-120b |
| Input price / 1M | $5 ↗ | — | — |
| Output price / 1M | $25 ↗ | — | — |
| Cached input / 1M | $0.5 ↗ | — | — |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $30 | — | — |
| Modalities | text · vision | text | Claude Opus 4.8 |
| Released | 2026-05-28 | 2025-08-05 | — |
| Cited benchmark scores | 17 | 6 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Claude Opus 4.8 vs …
Models sharing the most benchmarksMore matchups
gpt-oss-120b vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Claude Opus 4.8 and gpt-oss-120b on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.