Claude Opus 4.8
Official information
- Release date
- May 28, 2026
- Official model ID
- claude-opus-4-8
- Vendor source
- Claude Opus 4.8
- Identity verified
- Aug 13, 2026
API pricing
- Verification
- Verified
- Verified at
- Value benchmark tier
- claude-opus-4-8-standard
| Tier / region | Input / output · per MTok | Context pricing tier | Billing | Validity | Source |
|---|---|---|---|---|---|
claude-opus-4-8-standard global | $5 / $25 | No upper pricing tier | Standard online · Cache miss All day | Current | Official rates |
Rankings by category
Overall
#15High 0.8968.1
| Source | Percentile | Raw score | Config folding |
|---|---|---|---|
| Epoch AI | 83.7 | 158.3 | Single config |
| LiveBench | 67.1 | 77.1 | Single config |
| LMArena | 53.4 | 1456.8 | Median of 2 configs |
Cross-source percentile spread 30.3
Coding
#18High 0.7755.3
| Source | Percentile | Raw score | Config folding |
|---|---|---|---|
| DeepSWE | 37.5 | 51.8 | Median of 5 configs |
| LiveBench | 59.8 | 63.0 | Single config |
| LMArenatext-coding | 62.5 | 1488.0 | Median of 2 configs |
| · webdev | 75.0 | 1550.4 | Median of 2 configs |
Cross-source percentile spread 31.3
Agent
#11High 0.8460.2
| Source | Percentile | Raw score | Config folding |
|---|---|---|---|
| Agents' Last Exam | 61.4 | 45.1 | Single config |
| DeepSWE | 37.5 | 51.8 | Median of 5 configs |
| LMArena | 81.7 | 0.1 | Single config |
Cross-source percentile spread 44.2
Reasoning
#12High 0.9066.9
| Source | Percentile | Raw score | Config folding |
|---|---|---|---|
| Epoch AI | 53.7 | 0.9 | Median of 3 configs |
| LiveBench | 81.7 | 91.8 | Single config |
| LMArenatext-math | 70.2 | 1477.5 | Median of 2 configs |
| · text-hard | 60.2 | 1477.6 | Median of 2 configs |
Cross-source percentile spread 28.0
Value
#34High 0.8931.4
Aliases & configurations
- claude-opus-4-8
- claude-opus-4-8-high· high
- claude-opus-4-8-max-effort· max effort
- claude-opus-4-8-thinking· thinking