Compare / head-to-head
Claude Sonnet 4.5vso3
o3 leads 4 of 7 shared benchmarks. o3 is 1.8x cheaper per token. Both offer a 200K-token context window.
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
3 – 4
o3 leads
Cheaper per token
o3
1.8x cheaper, input + output
Larger context
Tie
both 200K tokens
Provider uptime (30d)
100% · 95.4674%
Anthropic · OpenAI
Claude Sonnet 4.5
Anthropic · released 2025-09-29
textvision
Quality
Benchmark matrix
7 shared · 13 only Claude Sonnet 4.5 · 0 only o3| Benchmark | Claude Sonnet 4.5 | o3 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 7 | ||||
| SWE-bench Verified | 77.2% ↗ | 69.1% ↗ | +8.1 pt | Claude Sonnet 4.5 |
| GPQA Diamond | 83.4% ↗ | 81.8% ↗epoch | +1.6 pt | Claude Sonnet 4.5 |
| AIME 2025 | 84.2% ↗matharena ⚠ | 89.2% ↗matharena ⚠ | -5 pt | o3 |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | 23.9% ↗epoch | 33.3% ↗epoch | -9.4 pt | o3 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 77.8% ↗epoch | 84.4% ↗epoch | -6.6 pt | o3 |
| SimpleQA Verified | 30.7% ↗epoch | 49.4% ↗epoch | -18.7 pt | o3 |
| SWE-bench Verified (Epoch AI run) | 71.3% ↗epoch | 62.3% ↗epoch | +9 pt | Claude Sonnet 4.5 |
| Only Claude Sonnet 4.5 reports · 13 | ||||
| Humanity's Last Exam (no tools) | 17.7% ↗ | not reported | — | — |
| ARC-AGI-2 (Verified) | 13.6% ↗ | not reported | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | 2.4% ↗epoch | not reported | — | — |
| GDPval-AA | 1276 ↗ | not reported | — | — |
| Humanity's Last Exam (with tools) | 33.6% ↗ | not reported | — | — |
| MCP Atlas | 43.8% ↗ | not reported | — | — |
| MMMLU | 89.5% ↗ | not reported | — | — |
| MMMU-Pro (no tools) | 63.4% ↗ | not reported | — | — |
| MMMU-Pro (with tools) | 68.9% ↗ | not reported | — | — |
| OSWorld-Verified | 61.4% ↗ | not reported | — | — |
| Tau2-bench Retail | 86.2% ↗ | not reported | — | — |
| Tau2-bench Telecom | 98% ↗ | not reported | — | — |
| Terminal-Bench 2.0 | 51% ↗ | not reported | — | — |
| Only o3 reports · 0 | ||||
| o3 reports nothing Claude Sonnet 4.5 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 Claude Sonnet 4.5 minus o3 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 Sonnet 4.5 | o3 | Edge |
|---|---|---|---|
| Context window | 200K tokens | 200K tokens | Tie |
| Max output | 64K tokens | 100K tokens | o3 |
| Input price / 1M | $3 ↗ | $2 ↗ | o3 |
| Output price / 1M | $15 ↗ | $8 ↗ | o3 |
| Cached input / 1M | $0.3 ↗ | $0.5 ↗ | Claude Sonnet 4.5 |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $18 | $10 | o3 |
| Modalities | text · vision | text · vision | Tie |
| Released | 2025-09-29 | 2025-04-16 | — |
| Cited benchmark scores | 21 | 7 | — |
Reliability
Provider status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Claude Sonnet 4.5 vs …
Models sharing the most benchmarksMore matchups
o3 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Claude Sonnet 4.5 and o3 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.