Model comparison
Claude 3.5 Haiku vs Sonar
Sonar is the stronger model overall, scoring 38.5 to 29.2 on the Noometry Index.
Last verified . 7 shared benchmarks.
PerplexitySummary
- They share 7 benchmarks with published results for both. Claude 3.5 Haiku scores higher in 0 categories and Sonar in 5 categories; 5 gaps are clear of the uncertainty.
- The widest gap is in math, where Sonar leads 33.7 to 14.7.
- The biggest single-benchmark swing is LiveBench Reasoning: 28.1% for Claude 3.5 Haiku and 46.3% for Sonar.
Side by side
| Claude 3.5 Haiku | Sonar | |
|---|---|---|
| Provider | Anthropic | Perplexity |
| Noometry Index | 29.2 | 38.5 |
| Released | 2024-10-22 | 2024-01-01 |
| Weights | Proprietary | Proprietary |
| Context window | — | 128K |
| Max output | — | 4K |
| Input $ / M tokens | — | $1 |
| Output $ / M tokens | — | $1 |
| Results tracked | 49 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Sonar leads
Claude 3.5 Haiku: 32.9 (#265), Sonar: 35.7 (#221)
| Benchmark | Claude 3.5 Haiku | Sonar |
|---|---|---|
| LiveBench Coding | 51.4% | 35.1% |
| Aider Polyglot | 28% | — |
| SciCode | 27.4% | — |
| WeirdML | 30.7% | — |
| BigCodeBench Instruct | 46.1% | — |
| LMArena Coding | 1286 | — |
| BigCodeBench Complete | 59% | — |
| CadEval | 32% | — |
Agentic & Tool Use Not comparable
Claude 3.5 Haiku: 28.0 (#95), Sonar: —
| Benchmark | Claude 3.5 Haiku | Sonar |
|---|---|---|
| BALROG | 19.3% | — |
Reasoning Sonar leads
Claude 3.5 Haiku: 17.7 (#290), Sonar: 21.1 (#227)
| Benchmark | Claude 3.5 Haiku | Sonar |
|---|---|---|
| LiveBench Reasoning | 28.1% | 46.3% |
| LiveBench Data Analysis | 48.5% | 37.9% |
| LiveBench | 43.5% | 46.9% |
| CritPt | 0% | — |
| LMArena Hard Prompts | 1251 | — |
| DTBench | 56.7% | — |
| Epoch Capabilities Index | 127.15 | — |
Math Sonar leads
Claude 3.5 Haiku: 14.7 (#300), Sonar: 33.7 (#200)
| Benchmark | Claude 3.5 Haiku | Sonar |
|---|---|---|
| LiveBench Math | 35.5% | 41.6% |
| OTIS Mock AIME 2024-2025 | 4.3% | — |
| Omni-MATH | 22.4% | — |
| LMArena Math | 1244 | — |
| MATH Level 5 | 46.4% | — |
| FrontierMath (Feb 2025 set) | 0.3% | — |
Knowledge Not comparable
Claude 3.5 Haiku: 18.7 (#281), Sonar: —
| Benchmark | Claude 3.5 Haiku | Sonar |
|---|---|---|
| GPQA Diamond | 38.1% | — |
| MMLU-Pro | 60.5% | — |
| Confabulations | 36.7% | — |
| GPQA (HELM) | 36.3% | — |
| LMArena Expert | 1208 | — |
| MMLU | 74.3% | — |
Multimodal Not comparable
Claude 3.5 Haiku: 26.8 (#117), Sonar: —
| Benchmark | Claude 3.5 Haiku | Sonar |
|---|---|---|
| LMArena Vision | 1092 | — |
| GeoBench | 34% | — |
Multilingual Not comparable
Claude 3.5 Haiku: 40.0 (#218), Sonar: —
| Benchmark | Claude 3.5 Haiku | Sonar |
|---|---|---|
| LMArena Non-English | 1238 | — |
| LMArena Chinese | 1229 | — |
| LMArena French | 1264 | — |
| LMArena German | 1237 | — |
| LMArena Japanese | 1175 | — |
| LMArena Korean | 1173 | — |
| LMArena Russian | 1253 | — |
| LMArena Spanish | 1261 | — |
Instruction Following Sonar leads
Claude 3.5 Haiku: 62.9 (#234), Sonar: 71.4 (#150)
| Benchmark | Claude 3.5 Haiku | Sonar |
|---|---|---|
| LiveBench Instruction Following | 61.9% | 76.2% |
| IFEval | 79.2% | — |
| LMArena Instruction Following | 1241 | — |
Long Context Not comparable
Claude 3.5 Haiku: 38.3 (#200), Sonar: —
| Benchmark | Claude 3.5 Haiku | Sonar |
|---|---|---|
| LMArena Longer Query | 1261 | — |
Writing & Preference Sonar leads
Claude 3.5 Haiku: 42.7 (#234), Sonar: 52.6 (#167)
| Benchmark | Claude 3.5 Haiku | Sonar |
|---|---|---|
| LiveBench Language | 35.4% | 44.1% |
| LMArena Text | 1255 | — |
| LMArena Creative Writing | 1233 | — |
| Short-Story Creative Writing | 73.5% | — |
| EQ-Bench Creative Writing | 1146 | — |
| WildBench | 76% | — |
| LMArena Multi-Turn | 1265 | — |
Frequently asked questions
Is Claude 3.5 Haiku better than Sonar?
Sonar is the stronger model overall, scoring 38.5 to 29.2 on the Noometry Index.
Is Claude 3.5 Haiku or Sonar better for coding?
Sonar scores higher on coding benchmarks: 35.7 versus 32.9 in the Noometry coding category.
How many benchmarks do Claude 3.5 Haiku and Sonar share?
7 benchmarks have published results for both models. Claude 3.5 Haiku has 49 scored results on Noometry and Sonar has 7.