Data points: 79
Model compare
The readout for Claude 3.5 Haiku and Claude Opus 4.6, before the detailed comparison sheet.
Weighted outcome: Claude Opus 4.6. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Decision read
Claude Opus 4.6
Claude Opus 4.6 has the higher weighted result; Model A / B score 4 to 96.
Evidence depth
79 data points
Includes 7 benchmark rows, 0 audit samples, and 7 provider examples.
Selection signal
Start with Claude Opus 4.6
The charts below split 14 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 3.5 Haiku and Claude Opus 4.6: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Model compare | Claude 3.5 Haiku | Claude Opus 4.6 |
|---|---|---|
| Overall leader | Contender | Leading |
| Weighted overall score | 4.0 pts | 96.0 pts |
| Benchmark category leads | 0 categories | 3 categories |
| Operational advantages | First-token latency | Cheapest input price, Average speed, Free providers, Provider coverage |
| Context window | 200K tokens | 1M tokens |
| Max output | 8.2K tokens | 128K tokens |
| Modalities | Input TextImage 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 3.5 Haiku | Claude Opus 4.6 |
|---|---|---|
| Developer | Anthropic | Anthropic |
| Released | Nov 2024 | Feb 2026 |
| Parameters | No data | No data |
| Tokenizer | Claude | Claude |
| Knowledge cutoff | 2024-07-31 | No data |
| OpenRouter ID | anthropic/claude-3.5-haiku | anthropic/claude-opus-4.6 |
| References | No data | No data |
This report only uses LMSpeed data for Claude 3.5 Haiku and Claude Opus 4.6: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
Claude 3.5 Haiku
Claude 3.5 Haiku has these operational advantages: First-token latency.
Claude Opus 4.6
Claude Opus 4.6 is stronger in benchmark categories (Coding, Reasoning, Math) and operational dimensions (Cheapest input price, Average speed, Free providers, 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 3.5 Haiku
41.4
Avg. score
Claude Opus 4.6
53.4
Claude Opus 4.6
Claude Opus 4.6 leads by 17.6
Claude Opus 4.6 leads by 14.4
Metric-level scores with benchmark source, rank depth, confidence, error, and evaluation date where available.
Claude 3.5 Haiku
winner$4.00/M
Rank #94/163 · confidence 4
Claude Opus 4.6
$25.00/M
Rank #148/163 · confidence 4
Claude 3.5 Haiku
winner$1.60/M
Rank #96/163 · confidence 4
Claude Opus 4.6
$10.00/M
Rank #148/163 · confidence 4
Claude 3.5 Haiku
winner$0.800/M
Rank #97/163 · confidence 4
Claude Opus 4.6
$5.00/M
Rank #147/163 · confidence 4
Claude 3.5 Haiku
63.4%
Rank #113/125 · confidence 4
Claude Opus 4.6
winner82.0%
Rank #47/125 · confidence 3 · eval date 2026-02-01
Claude 3.5 Haiku
40.8%
Rank #175/187 · confidence 4
Claude Opus 4.6
winner84.0%
Rank #52/187 · confidence 4
Claude 3.5 Haiku
3.5%
Rank #176/186 · confidence 4
Claude Opus 4.6
winner18.6%
Rank #61/186 · confidence 4
Claude 3.5 Haiku
27.4%
Rank #148/184 · confidence 4
Claude Opus 4.6
winner45.7%
Rank #32/184 · confidence 4
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | Claude 3.5 Haiku | Claude Opus 4.6 |
|---|---|---|
| No completed audits are available from shared providers yet. | ||
Speed aggregates and input/output pricing share each provider row for real API selection and migration cost checks.
| Provider | Claude 3.5 Haiku | Claude Opus 4.6 |
|---|---|---|
10 tests | Claude 3.5 Haiku claude-3-5-haiku-20241022 speed / latency N/A / N/A input / output $0.074/M/$0.371/M | Claude Opus 4.6 claude-opus-4-6 speed / latency 84 tok/s / 3916ms input / output $1.11/M/$5.54/M |
5 tests | Claude 3.5 Haiku speed / latency N/A / N/A input / output No data | Claude Opus 4.6 speed / latency 27 tok/s / 15402ms input / output No data |
5 tests | Claude 3.5 Haiku speed / latency 42 tok/s / 2458ms input / output No data | Claude Opus 4.6 speed / latency N/A / N/A input / output No data |
0 tests | Claude 3.5 Haiku speed / latency N/A / N/A input / output No data | Claude Opus 4.6 speed / latency N/A / N/A input / output No data |
0 tests | Claude 3.5 Haiku speed / latency N/A / N/A input / output No data | Claude Opus 4.6 speed / latency N/A / N/A input / output No data |
Claude 3.5 Haiku claude-3-5-haiku-20241022 speed / latency No data input / output $0.034/M/$0.171/M | Claude Opus 4.6 claude-opus-4-6 speed / latency No data input / output $1.37/M | |
Claude 3.5 Haiku claude-3-5-haiku-latest speed / latency No data input / output $0.035/M/$0.174/M | Claude Opus 4.6 claude-opus-4-6 speed / latency No data input / output $0.868/M |
Weighted outcome: Claude Opus 4.6. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Output
| Features | Text inputImage inputText outputTool calling | Text inputImage inputFile inputText outputTool callingStructured outputsJSON modeReasoning |
|---|
Claude Opus 4.6
Claude Opus 4.6 leads by 14.1
Claude Opus 4.6
Claude Opus 4.6
Claude Opus 4.6
