Compare / head-to-head
Claude Haiku 4.5vsClaude Opus 5
Claude Opus 5 leads 3 of 3 shared benchmarks. Claude Haiku 4.5 is 5x cheaper per token. Claude Opus 5 has the larger context window (1M tokens).
Benchmarks from cited public sources; pricing from official pages; status from official provider feeds.
Shared benchmarks
0 – 3
Claude Opus 5 leads
Cheaper per token
Claude Haiku 4.5
5x cheaper, input + output
Larger context
Claude Opus 5
1M tokens
Provider uptime (30d)
100%
Anthropic
Claude Haiku 4.5
Anthropic · released 2025-10-15
textvision
Claude Opus 5
Anthropic · released 2026-07-24
textvision
Quality
Benchmark matrix
3 shared · 1 only Claude Haiku 4.5 · 6 only Claude Opus 5| Benchmark | Claude Haiku 4.5 | Claude Opus 5 | Δ | Edge |
|---|---|---|---|---|
| Reported by both · 3 | ||||
| GPQA Diamond | 71.2% ↗epoch | 93.9% ↗epoch | -22.7 pt | Claude Opus 5 |
| OTIS Mock AIME 2024-2025 (Epoch AI run) | 66.7% ↗epoch | 98.9% ↗epoch | -32.2 pt | Claude Opus 5 |
| SimpleQA Verified | 13.2% ↗epoch | 59.9% ↗epoch | -46.7 pt | Claude Opus 5 |
| Only Claude Haiku 4.5 reports · 1 | ||||
| SWE-bench Verified | 73.3% ↗ | not reported | — | — |
| Only Claude Opus 5 reports · 6 | ||||
| Humanity's Last Exam (no tools) | not reported | 56.6% ↗ | — | — |
| CursorBench 3.2.0 | not reported | 70% ↗ | — | — |
| FrontierMath Tier 4 v2 (Epoch AI run) | not reported | 73.2% ↗epoch | — | — |
| FrontierMath Tiers 1-3 v2 (Epoch AI run) | not reported | 85.6% ↗epoch | — | — |
| GDPval-AA v2 | not reported | 1824 ↗ | — | — |
| Terminal-Bench Science 0.1 | not reported | 29% ↗ | — | — |
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 Haiku 4.5 minus Claude Opus 5 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 Haiku 4.5 | Claude Opus 5 | Edge |
|---|---|---|---|
| Context window | 200K tokens | 1M tokens | Claude Opus 5 |
| Max output | 64K tokens | 128K tokens | Claude Opus 5 |
| Input price / 1M | $1 ↗ | $5 ↗ | Claude Haiku 4.5 |
| Output price / 1M | $5 ↗ | $25 ↗ | Claude Haiku 4.5 |
| Cached input / 1M | $0.1 ↗ | $0.5 ↗ | Claude Haiku 4.5 |
| Input + output / 1M Lower is cheaper. List prices; batch, tool and regional fees excluded. | $6 | $30 | Claude Haiku 4.5 |
| Modalities | text · vision | text · vision | Tie |
| Released | 2025-10-15 | 2026-07-24 | — |
| Cited benchmark scores | 4 | 9 | — |
Reliability
Anthropic status
Last 60 days · refreshed daily on this page · live on /statusMore matchups
Claude Haiku 4.5 vs …
Models sharing the most benchmarksMore matchups
Claude Opus 5 vs …
Models sharing the most benchmarksBuilt by Respan
Which one wins on your data?
Public benchmarks are a starting point. Run Claude Haiku 4.5 and Claude Opus 5 on your own prompts with Respan evals, or route to either through one gateway key with automatic failover.