Data points: 148
Model compare
The readout for Claude Opus 4.6 and Claude Opus 5, before the detailed comparison sheet.
Weighted outcome: Claude Opus 5. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Decision read
Claude Opus 5
Claude Opus 5 has the higher weighted result; Model A / B score 20 to 80.
Evidence depth
148 data points
Includes 28 benchmark rows, 6 audit samples, and 7 provider examples.
Selection signal
Start with Claude Opus 5
The charts below split 41 high-signal samples across speed, scores, and audit health.
Switch either side of this report to compare another model with the same LMSpeed data pipeline.
Select a different model to open a new comparison URL.
This report only uses LMSpeed data for Claude Opus 4.6 and Claude Opus 5: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Model compare | Claude Opus 4.6 | Claude Opus 5 |
|---|---|---|
| Overall leader | Contender | Leading |
| Weighted overall score | 20.0 pts | 80.0 pts |
| Benchmark category leads | 0 categories | 6 categories |
| Operational advantages | Cheapest input price, Free providers, Provider coverage | No data |
| Context window | 1M tokens | 1M tokens |
| Max output | 128K tokens | 128K tokens |
| Modalities | Input TextImageFile Output Text | Input |
The overall result weights benchmark capability categories at 80% and price, API speed/latency, and availability at 20%. Recent test volume does not affect the winner, and missing benchmark categories are excluded.
| Model compare | Claude Opus 4.6 | Claude Opus 5 |
|---|---|---|
| Developer | Anthropic | Anthropic |
| Released | Feb 2026 | Jul 2026 |
| Parameters | No data | No data |
| Tokenizer | Claude | Claude |
| Knowledge cutoff | No data | No data |
| OpenRouter ID | anthropic/claude-opus-4.6 | anthropic/claude-opus-5 |
| References | No data | No data |
This report only uses LMSpeed data for Claude Opus 4.6 and Claude Opus 5: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
Claude Opus 4.6
Claude Opus 4.6 has these operational advantages: Cheapest input price, Free providers, Provider coverage.
Claude Opus 5
Claude Opus 5 leads these benchmark categories: Agents, Coding, Reasoning, Knowledge, Multilingual.
Third-party benchmark profile synced into LMSpeed; only metrics available for both models are shown.
Compare benchmark category scores on a 0-100 scale. Select a category to inspect the gap.
Avg. score
Claude Opus 4.6
53.4
Avg. score
Claude Opus 5
64.5
Claude Opus 5 leads by 11.8
Claude Opus 5 leads by 9.4
Claude Opus 5 leads by 6.7
Claude Opus 5 leads by 12.8
Claude Opus 4.6
Claude Opus 5 leads by 10.3
Claude Opus 5 leads by 10.2
Claude Opus 4.6
Metric-level scores with benchmark source, rank depth, confidence, error, and evaluation date where available.
Claude Opus 4.6
68.0
Rank #20/90 · confidence 3 · eval date 2026-02-01
Claude Opus 5
winner85.0
Rank #1/90 · confidence 3 · eval date 2026-07-24
Claude Opus 4.6
$5.00/M
Rank #152/169 · confidence 4
Claude Opus 5
$5.00/M
Rank #152/169 · confidence 4
Claude Opus 4.6
$10.00/M
Rank #153/169 · confidence 4
Claude Opus 5
$10.00/M
Rank #153/169 · confidence 4
Claude Opus 4.6
$25.00/M
Rank #153/169 · confidence 4
Claude Opus 5
$25.00/M
Rank #153/169 · confidence 4
Claude Opus 4.6
2.8
Rank #47/77 · confidence 3 · eval date 2026-02-01
Claude Opus 5
winner29.1
Rank #5/77 · confidence 3 · eval date 2026-07-24
Claude Opus 4.6
84.0%
Rank #57/194 · confidence 4
Claude Opus 5
winner93.2%
Rank #5/194 · confidence 4
Claude Opus 4.6
18.6%
Rank #67/193 · confidence 4
Claude Opus 5
winner52.6%
Rank #5/193 · confidence 4
Claude Opus 4.6
58.3
Rank #67/94 · confidence 3 · eval date 2026-02-01
Claude Opus 5
winner70.0
Rank #19/94 · confidence 3 · eval date 2026-07-24
Claude Opus 4.6
63.7
Rank #9/71 · confidence 3 · eval date 2026-02-01
Claude Opus 5
winner83.1
Rank #1/71 · confidence 3 · eval date 2026-07-24
Claude Opus 4.6
80.8
Rank #8/45 · confidence 3 · eval date 2026-02-01
Claude Opus 5
winner96.0
Rank #1/45 · confidence 3 · eval date 2026-07-24
Claude Opus 4.6
26.9
Rank #8/9 · confidence 3 · eval date 2026-02-01
Claude Opus 5
winner53.4
Rank #2/9 · confidence 3 · eval date 2026-07-24
Claude Opus 4.6
53.4
Rank #35/42 · confidence 3 · eval date 2026-02-01
Claude Opus 5
winner79.2
Rank #2/42 · confidence 3 · eval date 2026-07-24
Claude Opus 4.6
45.7%
Rank #37/191 · confidence 4
Claude Opus 5
winner55.7%
Rank #7/191 · confidence 4
Claude Opus 4.6
45.7
Rank #41/101 · confidence 3 · eval date 2026-02-01
Claude Opus 5
winner55.7
Rank #9/101 · confidence 3 · eval date 2026-07-24
Claude Opus 4.6
37.8
Rank #43/104 · confidence 3 · eval date 2026-02-01
Claude Opus 5
winner60.7
Rank #1/104 · confidence 3 · eval date 2026-07-24
Claude Opus 4.6
82.6
Rank #10/60 · confidence 3 · eval date 2026-02-01
Claude Opus 5
winner93.5
Rank #1/60 · confidence 3 · eval date 2026-07-24
Claude Opus 4.6
40.0
Rank #12/18 · confidence 3 · eval date 2026-02-01
Claude Opus 5
winner56.3
Rank #1/18 · confidence 3 · eval date 2026-07-24
Claude Opus 4.6
18.6
Rank #60/101 · confidence 3 · eval date 2026-02-01
Claude Opus 5
winner52.6
Rank #2/101 · confidence 3 · eval date 2026-07-24
Claude Opus 4.6
3.5
Rank #27/34 · confidence 3 · eval date 2026-02-01
Claude Opus 5
winner31.3
Rank #3/34 · confidence 3 · eval date 2026-07-24
Claude Opus 4.6
84.0
Rank #56/101 · confidence 3 · eval date 2026-02-01
Claude Opus 5
winner93.2
Rank #5/101 · confidence 3 · eval date 2026-07-24
Claude Opus 4.6
45.2
Rank #17/95 · confidence 3 · eval date 2026-02-01
Claude Opus 5
winner54.2
Rank #6/95 · confidence 3 · eval date 2026-07-24
Claude Opus 4.6
winner76.0
Rank #44/95 · confidence 3 · eval date 2026-02-01
Claude Opus 5
50.1
Rank #70/95 · confidence 3 · eval date 2026-07-24
Claude Opus 4.6
72.5
Rank #40/61 · confidence 3 · eval date 2026-02-01
Claude Opus 5
winner84.7
Rank #1/61 · confidence 3 · eval date 2026-07-24
Claude Opus 4.6
1319.0
Rank #8/69 · confidence 3 · eval date 2026-02-01
Claude Opus 5
winner1341.0
Rank #2/69 · confidence 3 · eval date 2026-07-24
Claude Opus 4.6
62.1
Rank #27/40 · confidence 3 · eval date 2026-02-01
Claude Opus 5
winner89.1
Rank #3/40 · confidence 3 · eval date 2026-07-24
Claude Opus 4.6
73.7
Rank #8/11 · confidence 3 · eval date 2026-02-01
Claude Opus 5
winner95.0
Rank #1/11 · confidence 3 · eval date 2026-07-24
Claude Opus 4.6
83.7
Rank #10/27 · confidence 3 · eval date 2026-02-01
Claude Opus 5
winner90.8
Rank #3/27 · confidence 3 · eval date 2026-07-24
Claude Opus 4.6
65.3
Rank #25/59 · confidence 3 · eval date 2026-02-01
Claude Opus 5
winner84.4
Rank #9/59 · confidence 3 · eval date 2026-07-24
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | Claude Opus 4.6 | Claude Opus 5 |
|---|---|---|
Winner: Claude Opus 4.6 | Claude Opus 4.6 claude-opus-4-6 Audit score 97 10010010088 | Claude Opus 5 claude-opus-5 No audit yet |
Winner: Claude Opus 4.6 | Claude Opus 4.6 claude-opus-4-6 Audit score 89 56100100100 | Claude Opus 5 claude-opus-5 No audit yet |
Winner: Claude Opus 4.6 | Claude Opus 4.6 claude-opus-4-6 Audit score 88 6410086100 | Claude Opus 5 claude-opus-5 No audit yet |
Winner: Claude Opus 4.6 | Claude Opus 4.6 claude-opus-4-6 Audit score 83 668480100 | Claude Opus 5 claude-opus-5 No audit yet |
Winner: Claude Opus 4.6 | Claude Opus 4.6 claude-opus-4-6 Audit score 80 668470100 | Claude Opus 5 claude-opus-5 No audit yet |
Winner: Claude Opus 4.6 | Claude Opus 4.6 claude-opus-4-6 Audit score 78 70728088 | Claude Opus 5 claude-opus-5 No audit yet |
Speed aggregates and input/output pricing share each provider row for real API selection and migration cost checks.
| Provider | Claude Opus 4.6 | Claude Opus 5 |
|---|---|---|
20 tests | Claude Opus 4.6 speed / latency 42 tok/s / 2282ms input / output No data | Claude Opus 5 speed / latency N/A / N/A input / output No data |
15 tests | Claude Opus 4.6 speed / latency 57 tok/s / 3926ms input / output No data | Claude Opus 5 speed / latency N/A / N/A input / output No data |
5 tests | Claude Opus 4.6 speed / latency 40 tok/s / 3103ms input / output No data | Claude Opus 5 speed / latency N/A / N/A input / output No data |
5 tests | Claude Opus 4.6 speed / latency 46 tok/s / 2559ms input / output No data | Claude Opus 5 speed / latency N/A / N/A input / output No data |
5 tests | Claude Opus 4.6 speed / latency 44 tok/s / 3353ms input / output No data | Claude Opus 5 speed / latency N/A / N/A input / output No data |
Claude Opus 4.6 claude-opus-4-6 speed / latency No data input / output $0/request | Claude Opus 5 claude-opus-5 speed / latency No data input / output $0/request | |
Claude Opus 4.6 claude-opus-4-6 speed / latency No data input / output $0/M/$0/M | Claude Opus 5 claude-opus-5 speed / latency No data input / output $0/M |
Weighted outcome: Claude Opus 5. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Output
| Features | Text inputImage inputFile inputText outputTool callingStructured outputsJSON modeReasoning | Text inputImage inputFile inputText outputTool callingStructured outputsJSON modeReasoning |
|---|
