GPT-4 vs Sonar Pro
Sonar Pro leads GPT-4 on the Artificial Analysis Intelligence Index, 7.6 to 6.7, and Sonar Pro costs 4.0x less per output token ($15.00 vs $60.00 per million). Updated October 21, 2026; 3 benchmarks have a result for both.
GPT-4 or Sonar Pro: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick GPT-4 for work measured by AA Intelligence Index or GPQA Diamond (Artificial Analysis run), where it leads.
- Shared results
- 3
- GPT-4 only
- 42
- Sonar Pro only
- 2
- Like-for-like categories
- 3 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
No call
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
Sonar Pro
Sonar Pro leads, 7.6 against 6.7.
Same board, both measured
Long documents
Listed context window
Sonar Pro
Sonar Pro takes 200K tokens against 8K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Sonar Pro
GPT-4 $0.060, Sonar Pro $0.011 per turn.
List prices
At a glance
- Coding index
- GPT-4 not benchmarked, Sonar Pro not benchmarked.
- Widest category
- Reasoning, 22.9 points apart on average over 1 shared benchmark.
- Widest single gap
- GPQA Diamond (Artificial Analysis run): GPT-4 34.9% against Sonar Pro 57.8%, 22.9 points apart on a 0 to 100 scale.
- Output price
- GPT-4 $60.00 against Sonar Pro $15.00 per million output tokens, 4.0x apart.
- Context window
- GPT-4 takes 8K tokens, Sonar Pro 200K.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | GPT-4 | Bars | Sonar Pro | Ties |
|---|---|---|---|---|
| Intelligence | 0 | 1 | ||
| Reasoning | 0 | 1 | ||
| Knowledge | 0 | 1 | ||
| All shared boards | 0 | 3 |
CodingDirectional onlySix of these boards feed the Vibe Coding Index7 boards, none shared
| Benchmark | GPT-4 | Sonar Pro | Leader |
|---|---|---|---|
| SWE-bench Verified | 22.4% | Not measured | Only GPT-4 measured |
| SWE-bench Lite | 39.7% | Not measured | Only GPT-4 measured |
| SWE-bench (full test set) | 12.5% | Not measured | Only GPT-4 measured |
| AA Coding Index | 13.1 | Not measured | Only GPT-4 measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 27.5% | Only Sonar Pro measured |
| LMArena Text: coding | 1209 | Not measured | Only GPT-4 measured |
| LMArena Text: software and IT | 1195 | Not measured | Only GPT-4 measured |
| Neither model has a result on the other 31 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GPT-4 | Sonar Pro | Leader |
|---|---|---|---|
| AA Intelligence Index | 6.7 | 7.6 | Sonar Pro |
| Epoch Capabilities Index | 125.7 | Not measured | Only GPT-4 measured |
Agentic workNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-4 | Sonar Pro | Leader |
|---|---|---|---|
| Neither model has a result on 39 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GPT-4 | Sonar Pro | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 34.9% | 57.8% | Sonar Pro |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 6.6% | Only Sonar Pro measured |
| BIG-Bench Hard | 75.1% | Not measured | Only GPT-4 measured |
| LMArena Text: hard prompts | 1200 | Not measured | Only GPT-4 measured |
| LMArena Text: expert | 1149 | Not measured | Only GPT-4 measured |
| LMArena Text: hard prompts in English | 1209 | Not measured | Only GPT-4 measured |
| Neither model has a result on the other 15 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | GPT-4 | Sonar Pro | Leader |
|---|---|---|---|
| GSM8K | 92.0% | Not measured | Only GPT-4 measured |
| LMArena Text: math | 1230 | Not measured | Only GPT-4 measured |
| LMArena Text: mathematical work | 1228 | Not measured | Only GPT-4 measured |
| Neither model has a result on the other 10 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GPT-4 | Sonar Pro | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 56.2% | 75.5% | Sonar Pro |
| MMLU | 86.4% | Not measured | Only GPT-4 measured |
| AI2 Reasoning Challenge | 96.3% | Not measured | Only GPT-4 measured |
| LMArena Text: science | 1177 | Not measured | Only GPT-4 measured |
| LMArena Text: medicine and healthcare | 1145 | Not measured | Only GPT-4 measured |
| LMArena Text: legal and government | 1191 | Not measured | Only GPT-4 measured |
| LMArena Text: business and finance | 1145 | Not measured | Only GPT-4 measured |
| Neither model has a result on the other 10 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-4 | Sonar Pro | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralDirectional onlyPublic boards, shown as published, kept out of the index22 boards, none shared
| Benchmark | GPT-4 | Sonar Pro | Leader |
|---|---|---|---|
| IFBench | 33.2% | Not measured | Only GPT-4 measured |
| DTBench | 62.7% | Not measured | Only GPT-4 measured |
| LMCA | 17.1% | Not measured | Only GPT-4 measured |
| HellaSwag | 95.3% | Not measured | Only GPT-4 measured |
| WinoGrande | 87.5% | Not measured | Only GPT-4 measured |
| LMArena Text | 1206 | Not measured | Only GPT-4 measured |
| LMArena Text: instruction following | 1201 | Not measured | Only GPT-4 measured |
| LMArena Text: creative writing | 1191 | Not measured | Only GPT-4 measured |
| LMArena Text: English | 1220 | Not measured | Only GPT-4 measured |
| LMArena Text: non-English | 1194 | Not measured | Only GPT-4 measured |
| LMArena Text: Chinese | 1184 | Not measured | Only GPT-4 measured |
| LMArena Text: German | 1198 | Not measured | Only GPT-4 measured |
| LMArena Text: Japanese | 1137 | Not measured | Only GPT-4 measured |
| LMArena Text: Korean | 1087 | Not measured | Only GPT-4 measured |
| LMArena Text: French | 1220 | Not measured | Only GPT-4 measured |
| LMArena Text: Spanish | 1197 | Not measured | Only GPT-4 measured |
| LMArena Text: Russian | 1195 | Not measured | Only GPT-4 measured |
| LMArena Text: Polish | 1265 | Not measured | Only GPT-4 measured |
| LMArena Text: multi-turn | 1206 | Not measured | Only GPT-4 measured |
| LMArena Text: longer queries | 1190 | Not measured | Only GPT-4 measured |
| LMArena Text: writing and language | 1219 | Not measured | Only GPT-4 measured |
| LMArena Text: entertainment and media | 1184 | Not measured | Only GPT-4 measured |
| Neither model has a result on the other 24 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-4 | Sonar Pro | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Sonar Pro costs less
Repository review
50K input + 3K output tokens
Sonar Pro costs less
Agent loop
200K input + 10K output tokens
Sonar Pro costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | OpenAI GPT-4 | Perplexity Sonar Pro |
|---|---|---|
| Maker | OpenAI | Perplexity |
| Weights | No public weights listed | No public weights listed |
| Released | May 28, 2023 | March 7, 2025 |
| Context window | 8K | 200K |
| Input $/Mtok | $30.00 | $3.00 |
| Output $/Mtok | $60.00 | $15.00 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 0 | 0 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-4 better than Sonar Pro for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GPT-4 for work measured by AA Intelligence Index or GPQA Diamond (Artificial Analysis run), where it leads.
Which is cheaper, GPT-4 or Sonar Pro?
GPT-4 costs $30.00 per million input tokens and $60.00 per million output tokens; Sonar Pro costs $3.00 and $15.00. Cost per solved task is known for neither of them.
Which has the bigger context window, GPT-4 or Sonar Pro?
Sonar Pro, with 200K tokens against 8K.
How many benchmarks is the GPT-4 vs Sonar Pro comparison based on?
3 benchmarks have a result for both models as of October 21, 2026. GPT-4's coding index rests on 0 independent benchmarks and Sonar Pro's on 0. Where only one model has a result, the page says so instead of naming a winner.