A
Anthropic
Claude Opus 4.8
- Model type
- Proprietary
- Evidence state
- Supported evidence
- Published context
- 1,000,000
Claude Opus 4.8 vs
Claude Opus 5
Read the published evidence, route context, and missing facts before making a local decision. This page does not name a universal winner.
Models in this comparison
Provider identity and evidence state stay balanced across the pair.
A
Anthropic
Claude Opus 5
- Model type
- Proprietary
- Evidence state
- Supported evidence
- Published context
- Not verified
Key implications
Broad shared-metric coverage. Each finding is tied to a published metric, price, context, or modality fact.
- Across compatible supported BenchLM categories, Claude Opus 5 has higher scores in Agentic, Knowledge, and Overall (and 2 more categories).
Shared metric view
The radar is a per-axis relative view; exact values and units remain available in its adjacent table.
- Claude Opus 4.8: solid line
- Claude Opus 5: dashed line
| Metric | Claude Opus 4.8 | Claude Opus 5 | Unit |
|---|---|---|---|
| Agentic | 61.78 | 80.13 | score |
| Coding | 71.98 | 78.41 | score |
| Knowledge | 86.8 | 97 | score |
| MultimodalGrounded | 85.4 | 85.9 | score |
| Overall | 76.6 | 83.06 | score |
Source metrics
Friendly metric names and published units stay visible. Missing measurements remain unavailable rather than becoming a score.
| Metric | Unit | Claude Opus 4.8 | Claude Opus 5 |
|---|---|---|---|
| Agentic | score | 61.78 | 80.13 |
| Coding | score | 71.98 | 78.41 |
| Knowledge | score | 86.8 | 97 |
| Math | score | 66.8 | Unavailable |
| MultimodalGrounded | score | 85.4 | 85.9 |
| Reasoning | score | 68.3 | 83.5 |
| Overall | score | 76.6 | 83.06 |
Agentic
- Unit
- score
- Claude Opus 4.8
- 61.78
- Claude Opus 5
- 80.13
Coding
- Unit
- score
- Claude Opus 4.8
- 71.98
- Claude Opus 5
- 78.41
Knowledge
- Unit
- score
- Claude Opus 4.8
- 86.8
- Claude Opus 5
- 97
Math
- Unit
- score
- Claude Opus 4.8
- 66.8
- Claude Opus 5
- Unavailable
MultimodalGrounded
- Unit
- score
- Claude Opus 4.8
- 85.4
- Claude Opus 5
- 85.9
Reasoning
- Unit
- score
- Claude Opus 4.8
- 68.3
- Claude Opus 5
- 83.5
Overall
- Unit
- score
- Claude Opus 4.8
- 76.6
- Claude Opus 5
- 83.06
Pricing and context
Verification is shown beside each selected route. Missing facts remain Not verified.
| Field | Unit | Claude Opus 4.8 | Claude Opus 5 |
|---|---|---|---|
| Input API price | USD / 1M tokens | $5 | $5 |
| Cached input API price | USD / 1M tokens | Not verified | $0.5 |
| Output API price | USD / 1M tokens | $25 | $25 |
| Route context | tokens | 1,000,000 | 1,000,000 |
| Input modalities | published list | Not verified | Not verified |
| Output modalities | published list | Not verified | Not verified |
Input API price
- Unit
- USD / 1M tokens
- Claude Opus 4.8
- $5
- Claude Opus 5
- $5
Cached input API price
- Unit
- USD / 1M tokens
- Claude Opus 4.8
- Not verified
- Claude Opus 5
- $0.5
Output API price
- Unit
- USD / 1M tokens
- Claude Opus 4.8
- $25
- Claude Opus 5
- $25
Route context
- Unit
- tokens
- Claude Opus 4.8
- 1,000,000
- Claude Opus 5
- 1,000,000
Input modalities
- Unit
- published list
- Claude Opus 4.8
- Not verified
- Claude Opus 5
- Not verified
Output modalities
- Unit
- published list
- Claude Opus 4.8
- Not verified
- Claude Opus 5
- Not verified
Evidence provenance
Source records, route identity, timestamps, and methodology are consolidated here without declaring either model a winner.
- Publication time
- Aug 30, 2026, 2:15 AM UTC
- Freshness
- Stale — Published weekly benchmark evidence has not refreshed within 8 days.
- Methodology
- benchlm: benchlm_raw_composite
- Model records
- Claude Opus 4.8 — source benchlm · artifact models · model claude-opus-4-8
- Claude Opus 5 — source benchlm · artifact models · model claude-opus-5
- Selected price routes
- Claude Opus 4.8 — route benchlm:claude-opus-4-8 · source benchlm · provider anthropic
- Claude Opus 5 — route benchlm:claude-opus-5 · source benchlm · provider anthropic
Keep comparing
Other reviewed matchups from the same published revision, ready to open without changing this result’s evidence.
Switch model pair
Choose from this result’s current and reviewed related models. Switching opens a reviewed comparison; it does not change this result’s evidence.
Step 1
Start with popular models, or search the full selectable directory.
Step 2
Start with popular models, or search the full selectable directory.