GPT-4 vs GPT-6 Sol
GPT-6 Sol leads GPT-4 on the Artificial Analysis Intelligence Index, 47.6 to 6.7, and GPT-6 Sol costs 6.0x less per output token ($10.00 vs $60.00 per million). Updated October 21, 2026; 32 benchmarks have a result for both.
vs boards won of 32 shared
GPT-4 or GPT-6 Sol: which to pick
Only GPT-6 Sol has a coding score, 76.0 on the Vibe Coding Index; GPT-4 has none, so the two cannot be ranked on coding.
Compare them on price, context and the boards below.
Model AGPT-4OpenAINot benchmarkedNo coding benchmarkNo cost per solved taskModel BGPT-6 SolOpenAI76.0/1005 independent benchmarksNo cost per solved task
- Shared results
- 32
- GPT-4 only
- 13
- GPT-6 Sol only
- 69
- Like-for-like categories
- 6 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
Only GPT-6 Sol has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
GPT-6 Sol
GPT-6 Sol leads, 47.6 against 6.7.
Same board, both measured
Web design
Design Arena: websites
No call
Only GPT-6 Sol has a Design Arena: websites result, 1292.
Directional only
Long documents
Listed context window
GPT-6 Sol
GPT-6 Sol takes 1.05M tokens against 8K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GPT-6 Sol
GPT-4 $0.060, GPT-6 Sol $0.0070 per turn.
List prices
At a glance
- Coding index
- GPT-4 not benchmarked, GPT-6 Sol 76.0 from 5 benchmarks.
- Widest category
- Intelligence, 44.2 points apart on average over 2 shared benchmarks.
- Widest single gap
- LMArena Text: expert: GPT-4 1149 against GPT-6 Sol 1437, 48.0 points apart on a 0 to 100 scale.
- Output price
- GPT-4 $60.00 against GPT-6 Sol $10.00 per million output tokens, 6.0x apart.
- Context window
- GPT-4 takes 8K tokens, GPT-6 Sol 1.05M.
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 | GPT-6 Sol | Ties |
|---|---|---|---|---|
| Coding | 0 | 2 | ||
| Intelligence | 0 | 2 | ||
| Reasoning | 0 | 3 | ||
| Math | 0 | 2 | ||
| Knowledge | 0 | 4 | ||
| General | 0 | 19 | ||
| All shared boards | 0 | 32 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index02
| Benchmark | GPT-4 | GPT-6 Sol | 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 |
| LiveBench coding | Not measured | 93.1% | Only GPT-6 Sol measured |
| LMArena WebDev | Not measured | 1683 | Only GPT-6 Sol measured |
| AA Coding Index | 13.1 | Not measured | Only GPT-4 measured |
| Terminal-Bench 4 (Vals AI) | Not measured | 44.4% | Only GPT-6 Sol measured |
| Vibe Code Bench (Vals AI) | Not measured | 87.8% | Only GPT-6 Sol measured |
| Code migration (Vals AI) | Not measured | 57.2% | Only GPT-6 Sol measured |
| ProgramBench (Vals AI) | Not measured | 2.0% | Only GPT-6 Sol measured |
| IOI (Vals AI) | Not measured | 82.6% | Only GPT-6 Sol measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 83.2% | Only GPT-6 Sol measured |
| CyberBench (Vals AI) | Not measured | 78.0% | Only GPT-6 Sol measured |
| SciCode | Not measured | 57.6% | Only GPT-6 Sol measured |
| FrontierCode | Not measured | 49.3% | Only GPT-6 Sol measured |
| ALE-Bench | Not measured | 2462.0 | Only GPT-6 Sol measured |
| LMArena Text: coding | 1209 | 1448 | GPT-6 Sol |
| LMArena Text: software and IT | 1195 | 1433 | GPT-6 Sol |
| LMArena WebDev: React | Not measured | 1685 | Only GPT-6 Sol measured |
| LMArena WebDev: HTML | Not measured | 1685 | Only GPT-6 Sol measured |
| LMArena WebDev: from an image | Not measured | 1660 | Only GPT-6 Sol measured |
| Neither model has a result on the other 18 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | GPT-4 | GPT-6 Sol | Leader |
|---|---|---|---|
| AA Intelligence Index | 6.7 | 47.6 | GPT-6 Sol |
| Epoch Capabilities Index | 125.7 | 163.7 | GPT-6 Sol |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index17 boards, none shared
| Benchmark | GPT-4 | GPT-6 Sol | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | Not measured | 1231 | Only GPT-6 Sol measured |
| Design Arena: agents building full-stack apps | Not measured | 1238 | Only GPT-6 Sol measured |
| Design Arena: agents building mobile apps | Not measured | 1214 | Only GPT-6 Sol measured |
| LiveBench research | Not measured | 69.3% | Only GPT-6 Sol measured |
| LiveBench browser | Not measured | 92.0% | Only GPT-6 Sol measured |
| LiveBench long agentic | Not measured | 66.9% | Only GPT-6 Sol measured |
| SREBench (Vals AI) | Not measured | 30.5% | Only GPT-6 Sol measured |
| Finance Agent (Vals AI) | Not measured | 49.0% | Only GPT-6 Sol measured |
| Tax Agent Bench (Vals AI) | Not measured | 15.0% | Only GPT-6 Sol measured |
| Legal Research Bench (Vals AI) | Not measured | 28.9% | Only GPT-6 Sol measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 71.5% | Only GPT-6 Sol measured |
| BioMysteryBench (Vals AI) | Not measured | 74.8% | Only GPT-6 Sol measured |
| Terminal-Bench-Science (Vals AI) | Not measured | 30.0% | Only GPT-6 Sol measured |
| Vals Science Index | Not measured | 45.0% | Only GPT-6 Sol measured |
| APEX-Agents | Not measured | 54.3% | Only GPT-6 Sol measured |
| SpireClimb | Not measured | 7.5% | Only GPT-6 Sol measured |
| Vending-Bench 2 | Not measured | $14,428 | Only GPT-6 Sol measured |
| Neither model has a result on the other 24 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | GPT-4 | GPT-6 Sol | Leader |
|---|---|---|---|
| LiveBench reasoning | Not measured | 88.7% | Only GPT-6 Sol measured |
| MysteryMechanism (Vals AI) | Not measured | 30.2% | Only GPT-6 Sol measured |
| GPQA Diamond (Artificial Analysis run) | 34.9% | Not measured | Only GPT-4 measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 47.9% | Only GPT-6 Sol measured |
| GPQA Diamond (Epoch AI run) | Not measured | 94.3% | Only GPT-6 Sol measured |
| ARC-AGI | Not measured | 95.5% | Only GPT-6 Sol measured |
| ARC-AGI-2 | Not measured | 89.6% | Only GPT-6 Sol measured |
| Chess puzzles | Not measured | 56.0% | Only GPT-6 Sol measured |
| Mystery game puzzles | Not measured | 56.0% | Only GPT-6 Sol measured |
| EBR-bench | Not measured | 53.3% | Only GPT-6 Sol measured |
| BIG-Bench Hard | 75.1% | Not measured | Only GPT-4 measured |
| LMArena Text: hard prompts | 1200 | 1422 | GPT-6 Sol |
| LMArena Text: expert | 1149 | 1437 | GPT-6 Sol |
| LMArena Text: hard prompts in English | 1209 | 1420 | GPT-6 Sol |
| LMArena Vision: diagrams | Not measured | 1270 | Only GPT-6 Sol measured |
| LMArena Vision: homework | Not measured | 1286 | Only GPT-6 Sol measured |
| Neither model has a result on the other 6 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | GPT-4 | GPT-6 Sol | Leader |
|---|---|---|---|
| OTIS Mock AIME | Not measured | 100.0% | Only GPT-6 Sol measured |
| FrontierMath, tiers 1 to 3 | Not measured | 89.8% | Only GPT-6 Sol measured |
| FrontierMath, tier 4 | Not measured | 90.0% | Only GPT-6 Sol measured |
| ProofBench | Not measured | 83.0% | Only GPT-6 Sol measured |
| GSM8K | 92.0% | Not measured | Only GPT-4 measured |
| LMArena Text: math | 1230 | 1407 | GPT-6 Sol |
| LMArena Text: mathematical work | 1228 | 1424 | GPT-6 Sol |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | GPT-4 | GPT-6 Sol | Leader |
|---|---|---|---|
| MedCode (Vals AI) | Not measured | 47.1% | Only GPT-6 Sol measured |
| MMLU Pro (Artificial Analysis run) | 56.2% | Not measured | Only GPT-4 measured |
| SimpleQA Verified | Not measured | 60.7% | Only GPT-6 Sol measured |
| MMLU | 86.4% | Not measured | Only GPT-4 measured |
| AI2 Reasoning Challenge | 96.3% | Not measured | Only GPT-4 measured |
| LMArena Text: science | 1177 | 1389 | GPT-6 Sol |
| LMArena Text: medicine and healthcare | 1145 | 1366 | GPT-6 Sol |
| LMArena Text: legal and government | 1191 | 1396 | GPT-6 Sol |
| LMArena Text: business and finance | 1145 | 1380 | GPT-6 Sol |
| FACTS Benchmark Suite | Not measured | 72.5% | Only GPT-6 Sol measured |
| Neither model has a result on the other 8 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | GPT-4 | GPT-6 Sol | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1292 | Only GPT-6 Sol measured |
| Design Arena: UI components | Not measured | 1292 | Only GPT-6 Sol measured |
| Design Arena: game dev | Not measured | 1314 | Only GPT-6 Sol measured |
| Design Arena: data viz | Not measured | 1269 | Only GPT-6 Sol measured |
| Design Arena: 3D | Not measured | 1318 | Only GPT-6 Sol measured |
| Design Arena: all code categories | Not measured | 1301 | Only GPT-6 Sol measured |
| Design Arena: SVG | Not measured | 1316 | Only GPT-6 Sol measured |
| Design Arena: ASCII art | Not measured | 1225 | Only GPT-6 Sol measured |
| LiveBench design | Not measured | 82.2% | Only GPT-6 Sol measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index019
| Benchmark | GPT-4 | GPT-6 Sol | Leader |
|---|---|---|---|
| LiveBench data analysis | Not measured | 81.2% | Only GPT-6 Sol measured |
| Public Benefits Bench (Vals AI) | Not measured | 56.6% | Only GPT-6 Sol measured |
| SAGE (Vals AI) | Not measured | 44.8% | Only GPT-6 Sol measured |
| MedScribe (Vals AI) | Not measured | 82.0% | Only GPT-6 Sol measured |
| IFBench | 33.2% | Not measured | Only GPT-4 measured |
| Long context reasoning (AA-LCR) | Not measured | 83.7% | Only GPT-6 Sol measured |
| DTBench | 62.7% | 97.3% | GPT-6 Sol |
| LMCA | 17.1% | 59.1% | GPT-6 Sol |
| Furniture assembly | Not measured | 58.3% | Only GPT-6 Sol measured |
| HellaSwag | 95.3% | Not measured | Only GPT-4 measured |
| WinoGrande | 87.5% | Not measured | Only GPT-4 measured |
| LMArena Text | 1206 | 1398 | GPT-6 Sol |
| LMArena Text: instruction following | 1201 | 1413 | GPT-6 Sol |
| LMArena Text: creative writing | 1191 | 1378 | GPT-6 Sol |
| LMArena Vision | Not measured | 1240 | Only GPT-6 Sol measured |
| LMArena Text: English | 1220 | 1396 | GPT-6 Sol |
| LMArena Text: non-English | 1194 | 1388 | GPT-6 Sol |
| LMArena Text: Chinese | 1184 | 1412 | GPT-6 Sol |
| LMArena Text: German | 1198 | 1379 | GPT-6 Sol |
| LMArena Text: Japanese | 1137 | 1377 | GPT-6 Sol |
| LMArena Text: Korean | 1087 | 1336 | GPT-6 Sol |
| LMArena Text: French | 1220 | 1399 | GPT-6 Sol |
| LMArena Text: Spanish | 1197 | 1387 | GPT-6 Sol |
| LMArena Text: Russian | 1195 | 1402 | GPT-6 Sol |
| LMArena Text: Polish | 1265 | 1372 | GPT-6 Sol |
| LMArena Text: multi-turn | 1206 | 1414 | GPT-6 Sol |
| LMArena Text: longer queries | 1190 | 1416 | GPT-6 Sol |
| LMArena Text: writing and language | 1219 | 1389 | GPT-6 Sol |
| LMArena Text: entertainment and media | 1184 | 1373 | GPT-6 Sol |
| LMArena Vision: English | Not measured | 1229 | Only GPT-6 Sol measured |
| LMArena Vision: reading text | Not measured | 1258 | Only GPT-6 Sol measured |
| LMArena Vision: creative writing | Not measured | 1219 | Only GPT-6 Sol measured |
| Neither model has a result on the other 14 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-4 | GPT-6 Sol | 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
GPT-4$0.060Fits in one request
GPT-6 Sol$0.0070Fits in one request
GPT-6 Sol costs less
Repository review
50K input + 3K output tokens
GPT-4$1.68Exceeds the context window
GPT-6 Sol$0.130Fits in one request
GPT-6 Sol costs less
Agent loop
200K input + 10K output tokens
GPT-4$6.60Exceeds the context window
GPT-6 Sol$0.500Fits in one request
GPT-6 Sol 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 | OpenAI GPT-6 Sol |
|---|---|---|
| Maker | OpenAI | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | May 28, 2023 | September 22, 2026 |
| Context window | 8K | 1.05M |
| Input $/Mtok | $30.00 | $2.00 |
| Output $/Mtok | $60.00 | $10.00 |
| Coding index | Not benchmarked | 76.0 |
| Independent measurements behind it | 0 | 5 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-4 better than GPT-6 Sol for coding?
Only GPT-6 Sol has a coding score, 76.0 on the Vibe Coding Index; GPT-4 has none, so the two cannot be ranked on coding. Compare them on price, context and the boards below.
Which is cheaper, GPT-4 or GPT-6 Sol?
GPT-4 costs $30.00 per million input tokens and $60.00 per million output tokens; GPT-6 Sol costs $2.00 and $10.00. Cost per solved task is known for neither of them.
Which has the bigger context window, GPT-4 or GPT-6 Sol?
GPT-6 Sol, with 1.05M tokens against 8K.
How many benchmarks is the GPT-4 vs GPT-6 Sol comparison based on?
32 benchmarks have a result for both models as of October 21, 2026. GPT-4's coding index rests on 0 independent benchmarks and GPT-6 Sol's on 5. Where only one model has a result, the page says so instead of naming a winner.