Comparison · Anthropic
Claude Opus 5.5 vs Claude Opus 5: pricing, allowances and benchmarks
Claude Opus 5.5 (Anthropic) and Claude Opus 5 (Anthropic): 4 shared subscriptions and 6 shared leaderboard snapshots, with workloads, sample dates and benchmark configurations.
Plan & benchmark data snapshot · How real prices are computed
As of 2026-10-16, 2 of 4 shared subscriptions use matching normalized workloads: Claude Opus 5.5 has a lower recorded token cost on 2, Claude Opus 5 on 0, with 0 tied. Their highest archived configurations score 57.62 and 50.78 on Artificial Analysis Intelligence Index v4.3; all 6 shared leaderboard snapshots, configurations and sources appear below.
- Shared subscriptions
- 4Both models available
- Comparable workloads
- 2Used for price ratios
- Shared leaderboards
- 6Highest archived configurations
- Official API prices
- 2/ 2Models with list prices
Plot both on the price–capability chart
Same plan, side by side
Each row is a subscription that includes both models at the same fee. Real cost = monthly fee ÷ the recorded monthly allowance. Each model's allowance assumes using the plan for that model; the columns cannot be added together. Click a price for its calculation and sources. Ratios use only matching normalized workloads.
| Plan / provider | Monthly fee | Claude Opus 5.5 | Claude Opus 5 | Recorded token cost |
|---|---|---|---|---|
| Claude ProAnthropic | $20/mo | $0.00655 /MTok 3.054B tokens/month Anthropic workload 2026-09-22 – 2026-09-27 · sampled · confidence High | $0.00772 /MTok 2.589B tokens/month Anthropic workload 2026-09-14 – 2026-09-22 · sampled · confidence High | Claude Opus 5.5 lower1.18× price ratio (higher/lower) |
| Claude Max 5x (9/14+)Anthropic | $100/mo | $0.00545 /MTok 18.334B tokens/month Anthropic workload 2026-09-29 – 2026-10-03 · sampled · confidence Medium | $0.01274 /MTok 7.85B tokens/month Not normalized 2026-08 · derived; uses the data date of Claude Max 20x (9/14+) · claude-opus-5 · confidence Medium | Unnormalized records |
| Claude Max 20x (9/14+)Anthropic | $200/mo | $0.00634 /MTok 31.538B tokens/month Anthropic workload 2026-09-22 – 2026-09-27 · sampled · confidence Medium | $0.01274 /MTok 15.7B tokens/month Not normalized 2026-08 · sampled · confidence Medium | Unnormalized records |
| Droid MaxFactory | $200/mo | $0.07918 /MTok 2.526B tokens/month Anthropic workload 2026-09-29 · sampled · confidence Medium | $0.09897 /MTok 2.021B tokens/month Anthropic workload 2026-09-29 · derived; uses the data date of Droid Max · claude-opus-5.5 · confidence Medium | Claude Opus 5.5 lower1.25× price ratio (higher/lower) |
Leaderboards head to head
Each model's highest archived configuration on each shared leaderboard snapshot, ranked among the models archived in this dataset. Harness, reasoning effort and service mode can differ; self-reported and estimated results are marked. These reference configurations are not measurements of the subscriptions above. Overlapping leaderboards do not form an overall ability rating.
| Leaderboard | Metric | Claude Opus 5.5 | Claude Opus 5 | Higher archived score |
|---|---|---|---|---|
| Artificial Analysis Intelligence Index v4.3 | Intelligence Index | 57.62 #1 / 60 · Claude Opus 5.5 (max with fallback) Max 2026-10-01 · Record | 50.78 #6 / 60 · Claude Opus 5 (max) Max 2026-10-01 · Record | Claude Opus 5.5+6.85 |
| Terminal-Bench 4.0 | Resolution Rate % | 66.4 self-reported #1 / 18 · Claude Code - Claude Opus 5.5 (default) - self-reported Claude Code 2026-09-23 · Record | 53.94 #4 / 18 · Claude Code - Opus 5 (xhigh) Claude Code · xhigh Reported interval 50.77–57.11 2026-10-01 · Record | Claude Opus 5.5+12.46 |
| Terminal-Bench 4.0 (AA) | Resolution Rate % | 59.6 #2 / 53 · Artificial Analysis - Claude Opus 5.5 (max with fallback) Artificial Analysis · Max 2026-10-01 · Record | 48.99 #6 / 53 · Artificial Analysis - Claude Opus 5 (max) Artificial Analysis · Max 2026-10-01 · Record | Claude Opus 5.5+10.61 |
| Code Arena | WebDev Overall | Arena Score | 1,818 #1 / 54 · claude-opus-5.5-max Max Reported interval 1,801.5–1,834.5 2026-10-01 · Record | 1,694 #6 / 54 · claude-opus-5-max Max Reported interval 1,687.5–1,700.5 2026-10-01 · Record | Claude Opus 5.5+124 |
| Agent Arena · Overall (Ranking / Pareto) | Net Improvement % | 13.78 #2 / 39 · Claude Opus 5.5 (High) High Reported interval 11.54–16.02 2026-10-01 · Record | 8.76 #5 / 39 · Claude Opus 5 (High) High Reported interval 7.26–10.26 2026-10-01 · Record | Claude Opus 5.5+5.02 |
| Artificial Analysis Coding Agent Index v1.5 | Coding Agent Index | 65.99 #2 / 19 · Claude Code - Opus 5.5 (max) Claude Code · Max 2026-10-01 · Record | 59.73 #6 / 19 · Claude Code - Opus 5 (max) Claude Code · Max 2026-10-01 · Record | Claude Opus 5.5+6.26 |
Official API pricing
Each row uses its listed pricing conditions. Cache writes are shown separately; subscription costs above retain their recorded quota basis. An em dash means that rate is not recorded.
| Model / pricing conditions | Cached input | Input | Cache write | Output |
|---|---|---|---|---|
| Claude Opus 5.5Upstream referenceUpstream price reference | $0.2 | $4 | — | $20 |
| Claude Opus 5Upstream referenceUpstream price reference | $0.5 | $5 | — | $25 |
How to read this comparison
Price ratios compare recorded USD/MTok under the same known workload. Raw measured totals, different workloads and unmetered access remain visible but are excluded from the lower-cost counts. Recorded allowances assume using the quota; your effective cost depends on utilization, cache mix, output mix and plan limits. Qualitative confidence is not an error bar.
- Anthropic workload: 97% cache reads / 2.5% cache writes / 0.5% output
- Not workload-normalized: sample lacks a token breakdown (or is an official absolute token table); raw tokens used as-is