Data points: 161
Model compare
The readout for Claude Opus 4.6 and Claude Opus 4.7, before the detailed comparison sheet.
Weighted outcome: Claude Opus 4.7. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Decision read
Claude Opus 4.7
Claude Opus 4.7 has the higher weighted result; Model A / B score 41.3 to 58.7.
Evidence depth
161 data points
Includes 31 benchmark rows, 6 audit samples, and 7 provider examples.
Selection signal
Start with Claude Opus 4.7
The charts below split 44 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 4.7: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Model compare | Claude Opus 4.6 | Claude Opus 4.7 |
|---|---|---|
| Overall leader | Contender | Leading |
| Weighted overall score | 41.3 pts | 58.7 pts |
| Benchmark category leads | 2 categories | 3 categories |
| Operational advantages | Provider coverage | Average speed, First-token latency |
| 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 4.7 |
|---|---|---|
| Developer | Anthropic | Anthropic |
| Released | Feb 2026 | May 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-4.7 |
| References | No data | No data |
This report only uses LMSpeed data for Claude Opus 4.6 and Claude Opus 4.7: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
Claude Opus 4.6
Claude Opus 4.6 is stronger in benchmark categories (Agents, Instruction following) and operational dimensions (Provider coverage).
Claude Opus 4.7
Claude Opus 4.7 is stronger in benchmark categories (Coding, Reasoning, Math) and operational dimensions (Average speed, First-token latency).
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 4.7
54.5
Claude Opus 4.6 leads by 0.6
Claude Opus 4.7 leads by 1.1
Claude Opus 4.7 leads by 2.6
Tied
Claude Opus 4.7 leads by 0.3
Claude Opus 4.6
Claude Opus 4.6
Claude Opus 4.6 leads by 0.3
Metric-level scores with benchmark source, rank depth, confidence, error, and evaluation date where available.
Claude Opus 4.6
winner68.0
Rank #17/84 · confidence 3 · eval date 2026-02-01
Claude Opus 4.7
66.0
Rank #20/84 · confidence 1 · eval date 2026-04-16
Claude Opus 4.6
$5.00/M
Rank #146/162 · confidence 4
Claude Opus 4.7
$5.00/M
Rank #146/162 · confidence 4
Claude Opus 4.6
$10.00/M
Rank #147/162 · confidence 4
Claude Opus 4.7
$10.00/M
Rank #147/162 · confidence 4
Claude Opus 4.6
$25.00/M
Rank #147/162 · confidence 4
Claude Opus 4.7
$25.00/M
Rank #147/162 · confidence 4
Claude Opus 4.6
84.0%
Rank #53/188 · confidence 4
Claude Opus 4.7
winner91.4%
Rank #13/188 · confidence 4
Claude Opus 4.6
18.6%
Rank #62/187 · confidence 4
Claude Opus 4.7
winner39.6%
Rank #14/187 · confidence 4
Claude Opus 4.6
2.8
Rank #43/73 · confidence 3 · eval date 2026-02-01
Claude Opus 4.7
winner5.1
Rank #33/73 · confidence 1 · eval date 2026-04-16
Claude Opus 4.6
58.3
Rank #62/89 · confidence 3 · eval date 2026-02-01
Claude Opus 4.7
winner67.0
Rank #34/89 · confidence 1 · eval date 2026-04-16
Claude Opus 4.6
57.6
Rank #5/33 · confidence 3 · eval date 2026-02-01
Claude Opus 4.7
winner71.0
Rank #1/33 · confidence 1 · eval date 2026-04-16
Claude Opus 4.6
winner84.1
Rank #3/12 · confidence 3 · eval date 2026-02-01
Claude Opus 4.7
82.8
Rank #4/12 · confidence 1 · eval date 2026-04-16
Claude Opus 4.6
26.9
Rank #7/8 · confidence 3 · eval date 2026-02-01
Claude Opus 4.7
winner38.5
Rank #5/8 · confidence 1 · eval date 2026-04-16
Claude Opus 4.6
45.7%
Rank #33/185 · confidence 4
Claude Opus 4.7
winner54.5%
Rank #7/185 · confidence 4
Claude Opus 4.6
winner63.7
Rank #8/65 · confidence 3 · eval date 2026-02-01
Claude Opus 4.7
63.2
Rank #11/65 · confidence 1 · eval date 2026-04-16
Claude Opus 4.6
45.7
Rank #37/96 · confidence 3 · eval date 2026-02-01
Claude Opus 4.7
winner50.1
Rank #21/96 · confidence 1 · eval date 2026-04-16
Claude Opus 4.6
22.9
Rank #10/35 · confidence 3 · eval date 2026-02-01
Claude Opus 4.7
winner22.9
Rank #9/35 · confidence 1 · eval date 2026-04-16
Claude Opus 4.6
40.7
Rank #10/47 · confidence 3 · eval date 2026-02-01
Claude Opus 4.7
winner43.8
Rank #9/47 · confidence 1 · eval date 2026-04-16
Claude Opus 4.6
59.8
Rank #22/56 · confidence 3 · eval date 2026-02-01
Claude Opus 4.7
winner61.9
Rank #21/56 · confidence 1 · eval date 2026-04-16
Claude Opus 4.6
winner82.6
Rank #8/55 · confidence 3 · eval date 2026-02-01
Claude Opus 4.7
62.8
Rank #36/55 · confidence 1 · eval date 2026-04-16
Claude Opus 4.6
3.5
Rank #23/29 · confidence 3 · eval date 2026-02-01
Claude Opus 4.7
winner14.2
Rank #13/29 · confidence 1 · eval date 2026-04-16
Claude Opus 4.6
winner45.2
Rank #15/90 · confidence 3 · eval date 2026-02-01
Claude Opus 4.7
43.5
Rank #17/90 · confidence 1 · eval date 2026-04-16
Claude Opus 4.6
37.8
Rank #39/99 · confidence 3 · eval date 2026-02-01
Claude Opus 4.7
winner42.7
Rank #20/99 · confidence 1 · eval date 2026-04-16
Claude Opus 4.6
18.6
Rank #56/96 · confidence 3 · eval date 2026-02-01
Claude Opus 4.7
winner31.2
Rank #30/96 · confidence 1 · eval date 2026-04-16
Claude Opus 4.6
84.0
Rank #52/96 · confidence 3 · eval date 2026-02-01
Claude Opus 4.7
winner88.5
Rank #31/96 · confidence 1 · eval date 2026-04-16
Claude Opus 4.6
winner76.0
Rank #44/90 · confidence 3 · eval date 2026-02-01
Claude Opus 4.7
51.9
Rank #64/90 · confidence 1 · eval date 2026-04-16
Claude Opus 4.6
1319.0
Rank #7/66 · confidence 3 · eval date 2026-02-01
Claude Opus 4.7
winner1320.0
Rank #5/66 · confidence 1 · eval date 2026-04-16
Claude Opus 4.6
72.5
Rank #36/57 · confidence 3 · eval date 2026-02-01
Claude Opus 4.7
winner76.4
Rank #21/57 · confidence 1 · eval date 2026-04-16
Claude Opus 4.6
winner44.6
Rank #61/86 · confidence 3 · eval date 2026-02-01
Claude Opus 4.7
43.6
Rank #63/86 · confidence 1 · eval date 2026-04-16
Claude Opus 4.6
19.9
Rank #4/19 · confidence 3 · eval date 2026-02-01
Claude Opus 4.7
winner20.7
Rank #2/19 · confidence 1 · eval date 2026-04-16
Claude Opus 4.6
61.9
Rank #10/50 · confidence 3 · eval date 2026-02-01
Claude Opus 4.7
winner65.6
Rank #3/50 · confidence 1 · eval date 2026-04-16
Claude Opus 4.6
65.3
Rank #22/53 · confidence 3 · eval date 2026-02-01
Claude Opus 4.7
winner73.1
Rank #16/53 · confidence 1 · eval date 2026-04-16
Claude Opus 4.6
winner84.8
Rank #44/84 · confidence 3 · eval date 2026-02-01
Claude Opus 4.7
74.0
Rank #60/84 · confidence 1 · eval date 2026-04-16
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | Claude Opus 4.6 | Claude Opus 4.7 |
|---|---|---|
Winner: Tie | Claude Opus 4.6 claude-opus-4-6 Audit score 97 10010010088 | Claude Opus 4.7 claude-opus-4-7 Audit score 97 10010010088 |
Winner: Claude Opus 4.6 | Claude Opus 4.6 claude-opus-4-6 Audit score 91 7610086100 | Claude Opus 4.7 claude-opus-4-7 No audit yet |
Winner: Claude Opus 4.7 | Claude Opus 4.6 claude-opus-4-6 No audit yet | Claude Opus 4.7 claude-opus-4-7 Audit score 91 64100100100 |
Winner: Claude Opus 4.7 | Claude Opus 4.6 claude-opus-4.6 No audit yet | Claude Opus 4.7 claude-opus-4-7 Audit score 89 848486100 |
Winner: Claude Opus 4.6 | Claude Opus 4.6 claude-opus-4-6 Audit score 89 56100100100 | Claude Opus 4.7 claude-opus-4-7 No audit yet |
Winner: Claude Opus 4.7 | Claude Opus 4.6 claude-opus-4-6 No audit yet | Claude Opus 4.7 claude-opus-4-7 Audit score 87 848480100 |
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 4.7 |
|---|---|---|
20 tests | Claude Opus 4.6 speed / latency 40 tok/s / 16141ms input / output No data | Claude Opus 4.7 speed / latency N/A / N/A input / output No data |
20 tests | Claude Opus 4.6 speed / latency 42 tok/s / 2282ms input / output No data | Claude Opus 4.7 speed / latency N/A / N/A input / output No data |
15 tests | Claude Opus 4.6 speed / latency N/A / N/A input / output No data | Claude Opus 4.7 speed / latency 35 tok/s / 2753ms input / output No data |
15 tests | Claude Opus 4.6 speed / latency N/A / N/A input / output No data | Claude Opus 4.7 speed / latency 38 tok/s / 3322ms input / output No data |
15 tests | Claude Opus 4.6 speed / latency 57 tok/s / 3926ms input / output No data | Claude Opus 4.7 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/M/$0/M | Claude Opus 4.7 claude-opus-4-7 speed / latency No data input / output $0/M | |
Claude Opus 4.6 claude-opus-4-6 speed / latency No data input / output $0/request | Claude Opus 4.7 claude-opus-4-7 speed / latency No data input / output $0/request |
Weighted outcome: Claude Opus 4.7. 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 |
|---|
