GPT-4 vs GPT-4o (2024-08-06)
Updated October 21, 2026. 32 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
GPT-4 and GPT-4o (2024-08-06) are level for coding, 22.4 against 23.1 on the Vibe Coding Index, so price and context decide.
Pick GPT-4 when what matters is SWE-bench Lite or MMLU, where it leads. Pick GPT-4o (2024-08-06) when output tokens cost 6.0x less, or when the context window is larger, 128K against 8K tokens.
- Shared results
- 32
- GPT-4 only
- 13
- GPT-4o (2024-08-06) only
- 26
- Like-for-like categories
- 6 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
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, four public coding benchmarks
No call
Level: 22.4 against 23.1, inside 2 points.
One benchmark behind each score
Intelligence
AA Intelligence Index
GPT-4o (2024-08-06)
GPT-4o (2024-08-06) leads, 7.7 against 6.7.
Same board, both measured
Math
AIME
No call
Only GPT-4o (2024-08-06) has a AIME result, 14.0%.
Directional only
Knowledge
MMLU Pro
No call
Only GPT-4o (2024-08-06) has a MMLU Pro result, 74.1%.
Directional only
Long documents
Listed context window
GPT-4o (2024-08-06)
GPT-4o (2024-08-06) takes 128K tokens against 8K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GPT-4o (2024-08-06)
GPT-4 $0.060, GPT-4o (2024-08-06) $0.0075 per turn.
List prices
At a glance
- Coding index
- GPT-4 22.4 from 1 benchmark, GPT-4o (2024-08-06) 23.1 from 1 benchmark.
- Widest category
- Coding, 14.8 points apart on average over 3 shared benchmarks.
- Widest single gap
- LMArena Text: Korean: GPT-4 1087 against GPT-4o (2024-08-06) 1218, 21.9 points apart on a 0 to 100 scale.
- Output price
- GPT-4 $60.00 against GPT-4o (2024-08-06) $10.00 per million output tokens, 6.0x apart.
- Context window
- GPT-4 takes 8K tokens, GPT-4o (2024-08-06) 128K.
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-4o (2024-08-06) | Ties |
|---|---|---|---|---|
| Coding | 1 | 2 | ||
| Intelligence | 0 | 1 | ||
| Reasoning | 0 | 4 | ||
| Math | 0 | 2 | ||
| Knowledge | 1 | 4 | ||
| General | 0 | 17 | ||
| All shared boards | 2 | 30 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index12
| Benchmark | GPT-4 | GPT-4o (2024-08-06) | Leader |
|---|---|---|---|
| Aider polyglot | Not measured | 23.1% | Only GPT-4o (2024-08-06) measured |
| SWE-bench Verified | 22.4% | Not measured | Only GPT-4 measured |
| SWE-bench Lite | 39.7% | 21.7% | GPT-4 |
| 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 | 31.7% | Only GPT-4o (2024-08-06) measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 8.3% | Only GPT-4o (2024-08-06) measured |
| LMArena Text: coding | 1209 | 1283 | GPT-4o (2024-08-06) |
| LMArena Text: software and IT | 1195 | 1278 | GPT-4o (2024-08-06) |
| Neither model has a result on the other 29 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GPT-4 | GPT-4o (2024-08-06) | Leader |
|---|---|---|---|
| AA Intelligence Index | 6.7 | 7.7 | GPT-4o (2024-08-06) |
| Epoch Capabilities Index | 125.7 | Not measured | Only GPT-4 measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | GPT-4 | GPT-4o (2024-08-06) | Leader |
|---|---|---|---|
| τ²-Bench Telecom | Not measured | 28.9% | Only GPT-4o (2024-08-06) measured |
| Neither model has a result on the other 38 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index04
| Benchmark | GPT-4 | GPT-4o (2024-08-06) | Leader |
|---|---|---|---|
| MMMU Pro (Vals AI) | Not measured | 64.0% | Only GPT-4o (2024-08-06) measured |
| GPQA Diamond (Artificial Analysis run) | 34.9% | 52.1% | GPT-4o (2024-08-06) |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 2.3% | Only GPT-4o (2024-08-06) measured |
| GPQA Diamond (Epoch AI run) | Not measured | 49.2% | Only GPT-4o (2024-08-06) measured |
| SimpleBench | Not measured | 17.8% | Only GPT-4o (2024-08-06) measured |
| Chess puzzles | Not measured | 6.0% | Only GPT-4o (2024-08-06) measured |
| BIG-Bench Hard | 75.1% | Not measured | Only GPT-4 measured |
| LMArena Text: hard prompts | 1200 | 1264 | GPT-4o (2024-08-06) |
| LMArena Text: expert | 1149 | 1241 | GPT-4o (2024-08-06) |
| LMArena Text: hard prompts in English | 1209 | 1277 | GPT-4o (2024-08-06) |
| Neither model has a result on the other 11 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | GPT-4 | GPT-4o (2024-08-06) | Leader |
|---|---|---|---|
| AIME | Not measured | 14.0% | Only GPT-4o (2024-08-06) measured |
| MATH 500 (Vals AI) | Not measured | 75.2% | Only GPT-4o (2024-08-06) measured |
| MGSM (Vals AI) | Not measured | 90.7% | Only GPT-4o (2024-08-06) measured |
| OTIS Mock AIME | Not measured | 6.4% | Only GPT-4o (2024-08-06) measured |
| FrontierMath, tiers 1 to 3 | Not measured | 0.4% | Only GPT-4o (2024-08-06) measured |
| MATH level 5 | Not measured | 53.3% | Only GPT-4o (2024-08-06) measured |
| GSM8K | 92.0% | Not measured | Only GPT-4 measured |
| LMArena Text: math | 1230 | 1285 | GPT-4o (2024-08-06) |
| LMArena Text: mathematical work | 1228 | 1283 | GPT-4o (2024-08-06) |
| Neither model has a result on the other 4 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index14
| Benchmark | GPT-4 | GPT-4o (2024-08-06) | Leader |
|---|---|---|---|
| MMLU Pro | Not measured | 74.1% | Only GPT-4o (2024-08-06) measured |
| LegalBench (Vals AI) | Not measured | 80.1% | Only GPT-4o (2024-08-06) measured |
| CorpFin (Vals AI) | Not measured | 39.4% | Only GPT-4o (2024-08-06) measured |
| TaxEval (Vals AI) | Not measured | 71.1% | Only GPT-4o (2024-08-06) measured |
| MortgageTax (Vals AI) | Not measured | 61.0% | Only GPT-4o (2024-08-06) measured |
| MedQA (Vals AI) | Not measured | 88.2% | Only GPT-4o (2024-08-06) measured |
| MMLU Pro (Artificial Analysis run) | 56.2% | Not measured | Only GPT-4 measured |
| SimpleQA Verified | Not measured | 26.0% | Only GPT-4o (2024-08-06) measured |
| MMLU | 86.4% | 84.3% | GPT-4 |
| AI2 Reasoning Challenge | 96.3% | Not measured | Only GPT-4 measured |
| LMArena Text: science | 1177 | 1274 | GPT-4o (2024-08-06) |
| LMArena Text: medicine and healthcare | 1145 | 1252 | GPT-4o (2024-08-06) |
| LMArena Text: legal and government | 1191 | 1275 | GPT-4o (2024-08-06) |
| LMArena Text: business and finance | 1145 | 1232 | GPT-4o (2024-08-06) |
| Neither model has a result on the other 3 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-4 | GPT-4o (2024-08-06) | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index017
| Benchmark | GPT-4 | GPT-4o (2024-08-06) | Leader |
|---|---|---|---|
| IFBench | 33.2% | 36.0% | GPT-4o (2024-08-06) |
| Long context reasoning (AA-LCR) | Not measured | 41.0% | Only GPT-4o (2024-08-06) 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 | 1283 | GPT-4o (2024-08-06) |
| LMArena Text: instruction following | 1201 | 1267 | GPT-4o (2024-08-06) |
| LMArena Text: creative writing | 1191 | 1274 | GPT-4o (2024-08-06) |
| LMArena Vision | Not measured | 1065 | Only GPT-4o (2024-08-06) measured |
| LMArena Text: English | 1220 | 1297 | GPT-4o (2024-08-06) |
| LMArena Text: non-English | 1194 | 1262 | GPT-4o (2024-08-06) |
| LMArena Text: Chinese | 1184 | 1254 | GPT-4o (2024-08-06) |
| LMArena Text: German | 1198 | 1257 | GPT-4o (2024-08-06) |
| LMArena Text: Japanese | 1137 | 1234 | GPT-4o (2024-08-06) |
| LMArena Text: Korean | 1087 | 1218 | GPT-4o (2024-08-06) |
| LMArena Text: French | 1220 | 1263 | GPT-4o (2024-08-06) |
| LMArena Text: Spanish | 1197 | 1269 | GPT-4o (2024-08-06) |
| LMArena Text: Russian | 1195 | 1272 | GPT-4o (2024-08-06) |
| LMArena Text: Polish | 1265 | Not measured | Only GPT-4 measured |
| LMArena Text: multi-turn | 1206 | 1279 | GPT-4o (2024-08-06) |
| LMArena Text: longer queries | 1190 | 1283 | GPT-4o (2024-08-06) |
| LMArena Text: writing and language | 1219 | 1290 | GPT-4o (2024-08-06) |
| LMArena Text: entertainment and media | 1184 | 1267 | GPT-4o (2024-08-06) |
| LMArena Vision: English | Not measured | 1072 | Only GPT-4o (2024-08-06) measured |
| LMArena Vision: Chinese | Not measured | 1009 | Only GPT-4o (2024-08-06) measured |
| Neither model has a result on the other 20 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-4 | GPT-4o (2024-08-06) | 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-4o (2024-08-06) costs less
Repository review
50K input + 3K output tokens
GPT-4o (2024-08-06) costs less
Agent loop
200K input + 10K output tokens
GPT-4o (2024-08-06) 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-4o (2024-08-06) |
|---|---|---|
| Maker | OpenAI | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | May 28, 2023 | August 6, 2024 |
| Context window | 8K | 128K |
| Input $/Mtok | $30.00 | $2.50 |
| Output $/Mtok | $60.00 | $10.00 |
| Coding index | 22.4 | 23.1 |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-4 better than GPT-4o (2024-08-06) for coding?
GPT-4 and GPT-4o (2024-08-06) are level for coding, 22.4 against 23.1 on the Vibe Coding Index, so price and context decide. Pick GPT-4 when what matters is SWE-bench Lite or MMLU, where it leads. Pick GPT-4o (2024-08-06) when output tokens cost 6.0x less, or when the context window is larger, 128K against 8K tokens.
Which is cheaper, GPT-4 or GPT-4o (2024-08-06)?
GPT-4 costs $30.00 per million input tokens and $60.00 per million output tokens; GPT-4o (2024-08-06) costs $2.50 and $10.00. Cost per solved task is known for neither of them.
Which has the bigger context window, GPT-4 or GPT-4o (2024-08-06)?
GPT-4o (2024-08-06), with 128K tokens against 8K.
How many benchmarks is the GPT-4 vs GPT-4o (2024-08-06) comparison based on?
32 benchmarks have a result for both models as of October 21, 2026. GPT-4's coding index rests on 1 independent benchmark and GPT-4o (2024-08-06)'s on 1. Where only one model has a result, the page says so instead of naming a winner.