Data points: 102
Model compare
The readout for Claude 3 Haiku and Claude Sonnet 4, before the detailed comparison sheet.
Weighted outcome: Claude Sonnet 4. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Decision read
Claude Sonnet 4
Claude Sonnet 4 has the higher weighted result; Model A / B score 0 to 100.
Evidence depth
102 data points
Includes 19 benchmark rows, 0 audit samples, and 7 provider examples.
Selection signal
Start with Claude Sonnet 4
The charts below split 26 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 Haiku and Claude Sonnet 4: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
| Model compare | Claude 3 Haiku | Claude Sonnet 4 |
|---|---|---|
| Overall leader | Contender | Leading |
| Weighted overall score | 0.0 pts | 100.0 pts |
| Benchmark category leads | 0 categories | 6 categories |
| Operational advantages | No data | Cheapest input price, Free providers, Provider coverage |
| Context window | 200K tokens | 1M tokens |
| Max output | 4.1K tokens | 64K tokens |
| Modalities | Input TextImage 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 3 Haiku | Claude Sonnet 4 |
|---|---|---|
| Developer | Anthropic | Anthropic |
| Released | Mar 2024 | May 2025 |
| Parameters | No data | No data |
| Tokenizer | Claude | Claude |
| Knowledge cutoff | 2023-08-31 | 2025-01-31 |
| OpenRouter ID | anthropic/claude-3-haiku | anthropic/claude-sonnet-4 |
| References | No data | No data |
This report only uses LMSpeed data for Claude 3 Haiku and Claude Sonnet 4: pricing, speed aggregates, third-party benchmark scores, and shared provider samples.
Claude 3 Haiku
Claude 3 Haiku does not clearly lead in the benchmark or operational dimensions shared by both models.
Claude Sonnet 4
Claude Sonnet 4 is stronger in benchmark categories (Agents, Coding, Reasoning, Knowledge, Math) and operational dimensions (Cheapest input price, 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 Haiku
37.5
Avg. score
Claude Sonnet 4
47.9
Claude Sonnet 4 leads by 6.5
Claude Sonnet 4 leads by 14.2
Claude Sonnet 4 leads by 12.5
Claude Sonnet 4 leads by 9.7
Claude Sonnet 4 leads by 16.8
No data
No data
Claude Sonnet 4 leads by 3.0
Metric-level scores with benchmark source, rank depth, confidence, error, and evaluation date where available.
Claude 3 Haiku
winner$0.250/M
Rank #36/162 · confidence 4
Claude Sonnet 4
$3.00/M
Rank #137/162 · confidence 4
Claude 3 Haiku
winner$0.500/M
Rank #40/162 · confidence 4
Claude Sonnet 4
$6.00/M
Rank #137/162 · confidence 4
Claude 3 Haiku
winner$1.25/M
Rank #50/162 · confidence 4
Claude Sonnet 4
$15.00/M
Rank #136/162 · confidence 4
Claude 3 Haiku
21.0
Rank #87/89 · confidence 1 · eval date 2024-03-01
Claude Sonnet 4
winner44.3
Rank #73/89 · confidence 1 · eval date 2025-05-01
Claude 3 Haiku
37.4%
Rank #180/188 · confidence 4
Claude Sonnet 4
winner68.3%
Rank #117/188 · confidence 4
Claude 3 Haiku
3.9%
Rank #165/187 · confidence 4
Claude Sonnet 4
winner4.0%
Rank #162/187 · confidence 4
Claude 3 Haiku
15.4%
Rank #111/115 · confidence 4
Claude Sonnet 4
winner44.9%
Rank #66/115 · confidence 4
Claude 3 Haiku
18.6
Rank #95/96 · confidence 1 · eval date 2024-03-01
Claude Sonnet 4
winner37.3
Rank #71/96 · confidence 1 · eval date 2025-05-01
Claude 3 Haiku
18.6%
Rank #177/185 · confidence 4
Claude Sonnet 4
winner37.3%
Rank #94/185 · confidence 4
Claude 3 Haiku
39.4%
Rank #73/74 · confidence 4
Claude Sonnet 4
winner93.4%
Rank #26/74 · confidence 4
Claude 3 Haiku
1.0%
Rank #67/68 · confidence 4
Claude Sonnet 4
winner40.7%
Rank #33/68 · confidence 4
Claude 3 Haiku
winner78.2
Rank #43/90 · confidence 1 · eval date 2024-03-01
Claude Sonnet 4
40.8
Rank #73/90 · confidence 1 · eval date 2025-05-01
Claude 3 Haiku
3.9
Rank #99/99 · confidence 1 · eval date 2024-03-01
Claude Sonnet 4
winner25.5
Rank #64/99 · confidence 1 · eval date 2025-05-01
Claude 3 Haiku
17.2
Rank #81/90 · confidence 1 · eval date 2024-03-01
Claude Sonnet 4
winner22.4
Rank #68/90 · confidence 1 · eval date 2025-05-01
Claude 3 Haiku
37.4
Rank #96/96 · confidence 1 · eval date 2024-03-01
Claude Sonnet 4
winner68.3
Rank #76/96 · confidence 1 · eval date 2025-05-01
Claude 3 Haiku
3.9
Rank #91/96 · confidence 1 · eval date 2024-03-01
Claude Sonnet 4
winner4.0
Rank #89/96 · confidence 1 · eval date 2025-05-01
Claude 3 Haiku
30.8
Rank #57/57 · confidence 1 · eval date 2024-03-01
Claude Sonnet 4
winner62.4
Rank #47/57 · confidence 1 · eval date 2025-05-01
Claude 3 Haiku
36.1
Rank #80/86 · confidence 1 · eval date 2024-03-01
Claude Sonnet 4
winner45.4
Rank #60/86 · confidence 1 · eval date 2025-05-01
Claude 3 Haiku
21.1
Rank #79/84 · confidence 1 · eval date 2024-03-01
Claude Sonnet 4
winner52.3
Rank #67/84 · confidence 1 · eval date 2025-05-01
Latest completed audits from shared providers, with four safety and integrity score groups plus report links.
| Provider | Claude 3 Haiku | Claude Sonnet 4 |
|---|---|---|
| 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 Haiku | Claude Sonnet 4 |
|---|---|---|
0 tests | Claude 3 Haiku speed / latency N/A / N/A input / output No data | Claude Sonnet 4 speed / latency N/A / N/A input / output No data |
0 tests | Claude 3 Haiku speed / latency N/A / N/A input / output No data | Claude Sonnet 4 speed / latency N/A / N/A input / output No data |
0 tests | Claude 3 Haiku speed / latency N/A / N/A input / output No data | Claude Sonnet 4 speed / latency N/A / N/A input / output No data |
0 tests | Claude 3 Haiku speed / latency N/A / N/A input / output No data | Claude Sonnet 4 speed / latency N/A / N/A input / output No data |
0 tests | Claude 3 Haiku speed / latency N/A / N/A input / output No data | Claude Sonnet 4 speed / latency N/A / N/A input / output No data |
Claude 3 Haiku claude-3-haiku-20240307 speed / latency No data input / output $0.030/M/$0.152/M | Claude Sonnet 4 claude-sonnet-4-20250514 speed / latency No data input / output $0.664/M | |
Claude 3 Haiku claude-3-haiku-20240307 speed / latency No data input / output $0.034/M/$0.171/M | Claude Sonnet 4 claude-sonnet-4-20250514 speed / latency No data input / output $0.822/M |
Weighted outcome: Claude Sonnet 4. Benchmark capability categories carry 80%, while price, API performance, and availability carry 20%.
Input
Output
| Features | Text inputImage inputText outputTool calling | Text inputImage inputFile inputText outputTool callingReasoning |
|---|
