Model comparison
Claude Haiku 4.5 vs Sonar
Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 38.5 on the Noometry Index. Sonar costs 2.0× less per token, which makes it the better buy when Claude Haiku 4.5's lead doesn't matter for your workload.
Last verified . 0 shared benchmarks.
PerplexitySummary
- The widest gap is in math, where Claude Haiku 4.5 leads 44.9 to 33.7.
- Sonar is cheaper at $1 / $1 per million input/output tokens, against $1 / $5 for Claude Haiku 4.5.
- Claude Haiku 4.5 accepts more context: 200K tokens versus 128K.
Side by side
| Claude Haiku 4.5 | Sonar | |
|---|---|---|
| Provider | Anthropic | Perplexity |
| Noometry Index | 39.5 | 38.5 |
| Released | 2025-10-15 | 2024-01-01 |
| Weights | Proprietary | Proprietary |
| Context window | 200K | 128K |
| Max output | 64K | 4K |
| Input $ / M tokens | $1 | $1 |
| Output $ / M tokens | $5 | $1 |
| Results tracked | 53 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding Claude Haiku 4.5 leads
Claude Haiku 4.5: 44.0 (#78), Sonar: 35.7 (#221)
| Benchmark | Claude Haiku 4.5 | Sonar |
|---|---|---|
| SWE-bench Verified (bash only) | 66.6% | — |
| LMArena WebDev | 1330 | — |
| SWE-bench Multilingual | 64.7% | — |
| SciCode | 43.3% | — |
| WeirdML | 45.4% | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1453 | — |
| ALE-Bench | 653.48 | — |
Agentic & Tool Use Not comparable
Claude Haiku 4.5: 33.6 (#52), Sonar: —
| Benchmark | Claude Haiku 4.5 | Sonar |
|---|---|---|
| Terminal-Bench | 35.5% | — |
| Berkeley Function Calling Leaderboard | 68.7% | — |
| DeepResearch Bench | 45.5% | — |
| BALROG | 31.2% | — |
| ExploitBench | 13.7% | — |
| Vending-Bench 2 | 458.89 | — |
Reasoning Sonar leads
Claude Haiku 4.5: 15.1 (#320), Sonar: 21.1 (#227)
| Benchmark | Claude Haiku 4.5 | Sonar |
|---|---|---|
| ARC-AGI-2 | 4% | — |
| NYT Connections (extended) | 14.3% | — |
| ARC-AGI-1 | 47.7% | — |
| CritPt | 0% | — |
| Chess Puzzles | 8% | — |
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1420 | — |
| DTBench | 73.6% | — |
| LiveBench Data Analysis | — | 37.9% |
| LMCA | 30.9% | — |
| Epoch Capabilities Index | 142.41 | — |
| ForecastBench | 61.4 | — |
| LiveBench | — | 46.9% |
Math Claude Haiku 4.5 leads
Claude Haiku 4.5: 44.9 (#78), Sonar: 33.7 (#200)
| Benchmark | Claude Haiku 4.5 | Sonar |
|---|---|---|
| OTIS Mock AIME 2024-2025 | 66.7% | — |
| Omni-MATH | 56.1% | — |
| LiveBench Math | — | 41.6% |
| LMArena Math | 1396 | — |
| MATH Level 5 | 96.4% | — |
| FrontierMath (Feb 2025 set) | 5.9% | — |
| FrontierMath Tier 4 (v1) | 2.1% | — |
Knowledge Not comparable
Claude Haiku 4.5: 37.7 (#153), Sonar: —
| Benchmark | Claude Haiku 4.5 | Sonar |
|---|---|---|
| GPQA Diamond | 71.2% | — |
| SimpleQA Verified | 13.2% | — |
| MMLU-Pro | 77.7% | — |
| Vectara Hallucination Rate | 9.8% | — |
| GPQA (HELM) | 60.5% | — |
| LMArena Expert | 1442 | — |
Multimodal Not comparable
Claude Haiku 4.5: 26.8 (#118), Sonar: —
| Benchmark | Claude Haiku 4.5 | Sonar |
|---|---|---|
| Blueprint-Bench 2 | 0% | — |
| LMArena Document | 1420 | — |
Multilingual Not comparable
Claude Haiku 4.5: 49.9 (#129), Sonar: —
| Benchmark | Claude Haiku 4.5 | Sonar |
|---|---|---|
| LMArena Non-English | 1377 | — |
| LMArena Chinese | 1417 | — |
| LMArena French | 1408 | — |
| LMArena German | 1375 | — |
| LMArena Japanese | 1339 | — |
| LMArena Korean | 1347 | — |
| LMArena Russian | 1381 | — |
| LMArena Spanish | 1420 | — |
Instruction Following Too close to call
Claude Haiku 4.5: 71.4 (#149), Sonar: 71.4 (#150)
| Benchmark | Claude Haiku 4.5 | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| IFEval | 80.1% | — |
| LMArena Instruction Following | 1414 | — |
Long Context Not comparable
Claude Haiku 4.5: 43.6 (#92), Sonar: —
| Benchmark | Claude Haiku 4.5 | Sonar |
|---|---|---|
| LMArena Longer Query | 1427 | — |
Writing & Preference Claude Haiku 4.5 leads
Claude Haiku 4.5: 57.9 (#123), Sonar: 52.6 (#167)
| Benchmark | Claude Haiku 4.5 | Sonar |
|---|---|---|
| LMArena Text | 1396 | — |
| LMArena Creative Writing | 1372 | — |
| WildBench | 83.9% | — |
| EQ-Bench 4 | 1064 | — |
| LMArena Multi-Turn | 1409 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is Claude Haiku 4.5 better than Sonar?
Claude Haiku 4.5 is the stronger model overall, scoring 39.5 to 38.5 on the Noometry Index. Sonar costs 2.0× less per token, which makes it the better buy when Claude Haiku 4.5's lead doesn't matter for your workload.
Which is cheaper, Claude Haiku 4.5 or Sonar?
Sonar is cheaper. It lists at $1 per million input tokens and $1 per million output tokens; Claude Haiku 4.5 lists at $1 and $5.
Is Claude Haiku 4.5 or Sonar better for coding?
Claude Haiku 4.5 scores higher on coding benchmarks: 44.0 versus 35.7 in the Noometry coding category.
Which has the bigger context window?
Claude Haiku 4.5 does, with 200K tokens against 128K.
How many benchmarks do Claude Haiku 4.5 and Sonar share?
0 benchmarks have published results for both models. Claude Haiku 4.5 has 53 scored results on Noometry and Sonar has 7.