Model comparison
DeepSeek V4 Pro vs Sonar
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 38.5 on the Noometry Index.
Last verified . 0 shared benchmarks.
DeepSeek
PerplexitySummary
- The widest gap is in reasoning, where DeepSeek V4 Pro leads 56.5 to 21.1.
- Both cost about the same: $0.66 input and $1.98 output per million tokens.
- DeepSeek V4 Pro accepts more context: 1M tokens versus 128K.
- DeepSeek V4 Pro has downloadable open weights; the other is API-only.
Side by side
| DeepSeek V4 Pro | Sonar | |
|---|---|---|
| Provider | DeepSeek | Perplexity |
| Noometry Index | 54.3 | 38.5 |
| Released | 2026-04-24 | 2024-01-01 |
| Weights | Open | Proprietary |
| Context window | 1M | 128K |
| Max output | 393K | 4K |
| Input $ / M tokens | $0.66 | $1 |
| Output $ / M tokens | $1.98 | $1 |
| Results tracked | 48 | 7 |
Sponsored placements are available on pages like this one. Advertise on Noometry
Category by category
Coding DeepSeek V4 Pro leads
DeepSeek V4 Pro: 52.4 (#34), Sonar: 35.7 (#221)
| Benchmark | DeepSeek V4 Pro | Sonar |
|---|---|---|
| SWE-bench Verified | 77.6% | — |
| FrontierCode | 28.6% | — |
| LMArena WebDev | 1582 | — |
| SciCode | 51% | — |
| WeirdML | 66.2% | — |
| LiveBench Coding | — | 35.1% |
| LMArena Coding | 1470 | — |
| ALE-Bench | 1,403 | — |
Agentic & Tool Use Not comparable
DeepSeek V4 Pro: 32.8 (#58), Sonar: —
| Benchmark | DeepSeek V4 Pro | Sonar |
|---|---|---|
| APEX-Agents | 47.3% | — |
| Vending-Bench 2 | 3,285 | — |
Reasoning DeepSeek V4 Pro leads
DeepSeek V4 Pro: 56.5 (#24), Sonar: 21.1 (#227)
| Benchmark | DeepSeek V4 Pro | Sonar |
|---|---|---|
| ARC-AGI-2 | 61.3% | — |
| Kagi LLM Benchmark | 53.5% | — |
| NYT Connections (extended) | 91.3% | — |
| ARC-AGI-1 | 90.5% | — |
| CritPt | 18% | — |
| Chess Puzzles | 47% | — |
| LiveBench Reasoning | — | 46.3% |
| LMArena Hard Prompts | 1461 | — |
| Mystery Game Puzzles | 43% | — |
| DTBench | 93.9% | — |
| LiveBench Data Analysis | — | 37.9% |
| LMCA | 45.5% | — |
| Surface Evolver Bench | 40% | — |
| Epoch Capabilities Index | 155.31 | — |
| ForecastBench | 56.1 | — |
| LiveBench | — | 46.9% |
Math DeepSeek V4 Pro leads
DeepSeek V4 Pro: 64.8 (#30), Sonar: 33.7 (#200)
| Benchmark | DeepSeek V4 Pro | Sonar |
|---|---|---|
| FrontierMath (Tiers 1-3) | 64.6% | — |
| FrontierMath Tier 4 | 26.8% | — |
| MathArena Final-Answer Competitions | 76.6% | — |
| OTIS Mock AIME 2024-2025 | 98.6% | — |
| ProofBench | 50% | — |
| LiveBench Math | — | 41.6% |
| LMArena Math | 1455 | — |
Knowledge Not comparable
DeepSeek V4 Pro: 59.5 (#31), Sonar: —
| Benchmark | DeepSeek V4 Pro | Sonar |
|---|---|---|
| GPQA Diamond | 91.7% | — |
| SimpleQA Verified | 52.9% | — |
| Vectara Hallucination Rate | 8.6% | — |
| LMArena Expert | 1464 | — |
Multilingual Not comparable
DeepSeek V4 Pro: 54.4 (#45), Sonar: —
| Benchmark | DeepSeek V4 Pro | Sonar |
|---|---|---|
| LMArena Non-English | 1439 | — |
| LMArena Chinese | 1486 | — |
| LMArena French | 1472 | — |
| LMArena German | 1458 | — |
| LMArena Japanese | 1445 | — |
| LMArena Korean | 1447 | — |
| LMArena Russian | 1453 | — |
| LMArena Spanish | 1458 | — |
Instruction Following DeepSeek V4 Pro leads
DeepSeek V4 Pro: 76.1 (#47), Sonar: 71.4 (#150)
| Benchmark | DeepSeek V4 Pro | Sonar |
|---|---|---|
| LiveBench Instruction Following | — | 76.2% |
| LMArena Instruction Following | 1448 | — |
Long Context Not comparable
DeepSeek V4 Pro: 45.0 (#51), Sonar: —
| Benchmark | DeepSeek V4 Pro | Sonar |
|---|---|---|
| CL-bench Life | 13.5% | — |
| LMArena Longer Query | 1458 | — |
Writing & Preference DeepSeek V4 Pro leads
DeepSeek V4 Pro: 65.5 (#46), Sonar: 52.6 (#167)
| Benchmark | DeepSeek V4 Pro | Sonar |
|---|---|---|
| LMArena Text | 1451 | — |
| LMArena Creative Writing | 1446 | — |
| EQ-Bench Creative Writing | 1553 | — |
| EQ-Bench 4 | 1166 | — |
| LMArena Multi-Turn | 1467 | — |
| LiveBench Language | — | 44.1% |
Frequently asked questions
Is DeepSeek V4 Pro better than Sonar?
DeepSeek V4 Pro is the stronger model overall, scoring 54.3 to 38.5 on the Noometry Index.
Which is cheaper, DeepSeek V4 Pro or Sonar?
DeepSeek V4 Pro is cheaper. It lists at $0.66 per million input tokens and $1.98 per million output tokens; Sonar lists at $1 and $1.
Is DeepSeek V4 Pro or Sonar better for coding?
DeepSeek V4 Pro scores higher on coding benchmarks: 52.4 versus 35.7 in the Noometry coding category.
Which has the bigger context window?
DeepSeek V4 Pro does, with 1M tokens against 128K.
How many benchmarks do DeepSeek V4 Pro and Sonar share?
0 benchmarks have published results for both models. DeepSeek V4 Pro has 48 scored results on Noometry and Sonar has 7.