Data points: 146
Model compare
The readout for Claude Opus 4.5 and Claude Sonnet 4.6, before the detailed comparison sheet.
Weighted outcome: Claude Sonnet 4.6. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Decision read
Claude Sonnet 4.6
Claude Sonnet 4.6 has the higher weighted result; Model A / B score 46.3 to 53.7.
Evidence depth
146 data points
Includes 36 benchmark rows, 2 audit samples, and 6 provider examples.
Selection signal
Start with Claude Sonnet 4.6
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 4.5 and Claude Sonnet 4.6: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Model compare | Claude Opus 4.5 | Claude Sonnet 4.6 |
|---|---|---|
| Overall leader | Contender | Leading |
| Weighted overall score | 46.3 pts | 53.7 pts |
| Benchmark category leads | 3 categories | 4 categories |
| Operational advantages | Average speed, First-token latency, Free providers | Cheapest input price, Provider coverage |
| Context window | 200K tokens | 1M tokens |
| Max output | 64K tokens | 128K tokens |
| Modalities | Input FileImageText Output Text |
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 4.5 | Claude Sonnet 4.6 |
|---|---|---|
| Developer | Anthropic | Anthropic |
| Released | Nov 2025 | Feb 2026 |
| Parameters | No data | No data |
| Tokenizer | Claude | Claude |
| Knowledge cutoff | No data | No data |
| OpenRouter ID | anthropic/claude-opus-4.5 | anthropic/claude-sonnet-4.6 |
| References | No data | No data |
This report only uses LMSpeed data for Claude Opus 4.5 and Claude Sonnet 4.6: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
Claude Opus 4.5
Claude Opus 4.5 is stronger in benchmark categories (Coding, Reasoning, Instruction following) and operational dimensions (Average speed, First-token latency, Free providers).
Claude Sonnet 4.6
Claude Sonnet 4.6 is stronger in benchmark categories (Agents, Knowledge, Math, Multimodal) and operational dimensions (Cheapest input price, Provider coverage).
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 4.5
50.7
Avg. score
Claude Sonnet 4.6
53.2
Claude Sonnet 4.6 leads by 3.6
Claude Opus 4.5 leads by 1.0
Claude Opus 4.5 leads by 12.5
Metric-level scores with benchmark source, rank depth, confidence, error, and evaluation date where available.
Claude Opus 4.5
59.0
Rank #31/84 · confidence 4 · eval date 2025-11-01
Claude Sonnet 4.6
winner63.0
Rank #25/84 · confidence 3 · eval date 2026-02-01
Claude Opus 4.5
$25.00/M
Rank #147/162 · confidence 4
Claude Sonnet 4.6
winner$15.00/M
Rank #136/162 · confidence 4
Claude Opus 4.5
$10.00/M
Rank #147/162 · confidence 4
Claude Sonnet 4.6
winner$6.00/M
Rank #137/162 · confidence 4
Claude Opus 4.5
$5.00/M
Rank #146/162 · confidence 4
Claude Sonnet 4.6
winner$3.00/M
Rank #137/162 · confidence 4
Claude Opus 4.5
winner88.9%
Rank #4/125 · confidence 4
Claude Sonnet 4.6
79.2%
Rank #68/125 · confidence 3 · eval date 2026-02-01
Claude Opus 4.5
81.0%
Rank #73/188 · confidence 4
Claude Sonnet 4.6
winner87.5%
Rank #31/188 · confidence 4
Claude Opus 4.5
12.9%
Rank #80/187 · confidence 4
Claude Sonnet 4.6
winner30.0%
Rank #31/187 · confidence 4
Claude Opus 4.5
winner65.3
Rank #44/89 · confidence 4 · eval date 2025-11-01
Claude Sonnet 4.6
57.7
Rank #63/89 · confidence 3 · eval date 2026-02-01
Claude Opus 4.5
0.3
Rank #68/73 · confidence 4 · eval date 2025-11-01
Claude Sonnet 4.6
winner0.9
Rank #60/73 · confidence 3 · eval date 2026-02-01
Claude Opus 4.5
winner80.9
Rank #6/43 · confidence 4 · eval date 2025-11-01
Claude Sonnet 4.6
79.6
Rank #13/43 · confidence 3 · eval date 2026-02-01
Claude Opus 4.5
54.2
Rank #31/65 · confidence 4 · eval date 2025-11-01
Claude Sonnet 4.6
winner63.7
Rank #8/65 · confidence 3 · eval date 2026-02-01
Claude Opus 4.5
winner47.0%
Rank #25/185 · confidence 4
Claude Sonnet 4.6
46.8%
Rank #29/185 · confidence 4
Claude Opus 4.5
winner47.0
Rank #31/96 · confidence 4 · eval date 2025-11-01
Claude Sonnet 4.6
46.9
Rank #33/96 · confidence 3 · eval date 2026-02-01
Claude Opus 4.5
20.7
Rank #29/47 · confidence 4 · eval date 2025-11-01
Claude Sonnet 4.6
winner32.4
Rank #18/47 · confidence 3 · eval date 2026-02-01
Claude Opus 4.5
4.2
Rank #23/35 · confidence 4 · eval date 2025-11-01
Claude Sonnet 4.6
winner8.3
Rank #19/35 · confidence 3 · eval date 2026-02-01
Claude Opus 4.5
winner58.6
Rank #23/56 · confidence 4 · eval date 2025-11-01
Claude Sonnet 4.6
49.5
Rank #31/56 · confidence 3 · eval date 2026-02-01
Claude Opus 4.5
70.6
Rank #7/16 · confidence 4 · eval date 2025-11-01
Claude Sonnet 4.6
winner95.0
Rank #1/16 · confidence 3 · eval date 2026-02-01
Claude Opus 4.5
61.0
Rank #38/55 · confidence 4 · eval date 2025-11-01
Claude Sonnet 4.6
winner76.9
Rank #18/55 · confidence 3 · eval date 2026-02-01
Claude Opus 4.5
winner40.7
Rank #20/90 · confidence 4 · eval date 2025-11-01
Claude Sonnet 4.6
38.0
Rank #29/90 · confidence 3 · eval date 2026-02-01
Claude Opus 4.5
34.7
Rank #48/99 · confidence 4 · eval date 2025-11-01
Claude Sonnet 4.6
winner35.9
Rank #43/99 · confidence 3 · eval date 2026-02-01
Claude Opus 4.5
winner75.4
Rank #45/90 · confidence 4 · eval date 2025-11-01
Claude Sonnet 4.6
65.9
Rank #57/90 · confidence 3 · eval date 2026-02-01
Claude Opus 4.5
winner81.0
Rank #60/96 · confidence 4 · eval date 2025-11-01
Claude Sonnet 4.6
79.9
Rank #63/96 · confidence 3 · eval date 2026-02-01
Claude Opus 4.5
12.9
Rank #65/96 · confidence 4 · eval date 2025-11-01
Claude Sonnet 4.6
winner13.2
Rank #63/96 · confidence 3 · eval date 2026-02-01
Claude Opus 4.5
1277.0
Rank #24/66 · confidence 4 · eval date 2025-11-01
Claude Sonnet 4.6
winner1314.0
Rank #8/66 · confidence 3 · eval date 2026-02-01
Claude Opus 4.5
68.5
Rank #20/22 · confidence 4 · eval date 2025-11-01
Claude Sonnet 4.6
winner77.4
Rank #17/22 · confidence 3 · eval date 2026-02-01
Claude Opus 4.5
29.4
Rank #33/35 · confidence 4 · eval date 2025-11-01
Claude Sonnet 4.6
winner57.5
Rank #25/35 · confidence 3 · eval date 2026-02-01
Claude Opus 4.5
winner71.2
Rank #39/57 · confidence 4 · eval date 2025-11-01
Claude Sonnet 4.6
70.6
Rank #40/57 · confidence 3 · eval date 2026-02-01
Claude Opus 4.5
winner43.0
Rank #64/86 · confidence 4 · eval date 2025-11-01
Claude Sonnet 4.6
41.2
Rank #69/86 · confidence 3 · eval date 2026-02-01
Claude Opus 4.5
59.6
Rank #15/28 · confidence 4 · eval date 2025-11-01
Claude Sonnet 4.6
winner67.8
Rank #5/28 · confidence 3 · eval date 2026-02-01
Claude Opus 4.5
32.3
Rank #9/20 · confidence 4 · eval date 2025-11-01
Claude Sonnet 4.6
winner36.9
Rank #5/20 · confidence 3 · eval date 2026-02-01
Claude Opus 4.5
winner64.2
Rank #6/50 · confidence 4 · eval date 2025-11-01
Claude Sonnet 4.6
62.9
Rank #8/50 · confidence 3 · eval date 2026-02-01
Claude Opus 4.5
50.6
Rank #10/11 · confidence 4 · eval date 2025-11-01
Claude Sonnet 4.6
winner65.2
Rank #9/11 · confidence 3 · eval date 2026-02-01
Claude Opus 4.5
66.3
Rank #14/21 · confidence 4 · eval date 2025-11-01
Claude Sonnet 4.6
winner72.1
Rank #11/21 · confidence 3 · eval date 2026-02-01
Claude Opus 4.5
winner59.3
Rank #28/46 · confidence 4 · eval date 2025-11-01
Claude Sonnet 4.6
59.1
Rank #30/46 · confidence 3 · eval date 2026-02-01
Claude Opus 4.5
48.2
Rank #36/53 · confidence 4 · eval date 2025-11-01
Claude Sonnet 4.6
winner55.0
Rank #30/53 · confidence 3 · eval date 2026-02-01
Claude Opus 4.5
winner86.3
Rank #39/84 · confidence 4 · eval date 2025-11-01
Claude Sonnet 4.6
79.5
Rank #55/84 · confidence 3 · eval date 2026-02-01
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | Claude Opus 4.5 | Claude Sonnet 4.6 |
|---|---|---|
Winner: Claude Sonnet 4.6 | Claude Opus 4.5 claude-opus-4-5-20251101 No audit yet | Claude Sonnet 4.6 claude-sonnet-4-6 Audit score 94 76100100100 |
Winner: Claude Sonnet 4.6 | Claude Opus 4.5 claude-opus-4-5-20251101 No audit yet | Claude Sonnet 4.6 claude-sonnet-4-6 Audit score 89 56100100100 |
Speed aggregates and input/output pricing share each provider row for real API selection and migration cost checks.
| Provider | Claude Opus 4.5 | Claude Sonnet 4.6 |
|---|---|---|
25 tests | Claude Opus 4.5 speed / latency N/A / N/A input / output No data | Claude Sonnet 4.6 speed / latency 40 tok/s / 3145ms input / output No data |
20 tests | Claude Opus 4.5 speed / latency 56 tok/s / 2598ms input / output No data | Claude Sonnet 4.6 speed / latency 55 tok/s / 2094ms input / output No data |
10 tests | Claude Opus 4.5 speed / latency N/A / N/A input / output No data | Claude Sonnet 4.6 speed / latency 41 tok/s / 3714ms input / output No data |
10 tests | Claude Opus 4.5 speed / latency N/A / N/A input / output No data | Claude Sonnet 4.6 speed / latency 86 tok/s / 1831ms input / output No data |
10 tests | Claude Opus 4.5 speed / latency N/A / N/A input / output No data | Claude Sonnet 4.6 speed / latency 31 tok/s / 4124ms input / output No data |
Claude Opus 4.5 claude-opus-4-5-20251101 speed / latency No data input / output $0/request | Claude Sonnet 4.6 claude-sonnet-4-6 speed / latency No data input / output $0/request |
Weighted outcome: Claude Sonnet 4.6. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Input
Output
| Features | Text inputImage inputFile inputText outputTool callingStructured outputsJSON modeReasoning | Text inputImage inputFile inputText outputTool callingStructured outputsJSON modeReasoning |
|---|
Claude Sonnet 4.6 leads by 13.0
Claude Sonnet 4.6 leads by 3.4
Claude Opus 4.5
Claude Sonnet 4.6 leads by 13.4
Claude Opus 4.5 leads by 1.9
