GPT-4 vs o3 Pro
o3 Pro leads GPT-4 on the Artificial Analysis Intelligence Index, 21.9 to 6.7, and GPT-4 costs 1.3x less per output token ($60.00 vs $80.00 per million). Updated October 22, 2026; 5 benchmarks have a result for both.
GPT-4 or o3 Pro: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick GPT-4 for output tokens 1.3x cheaper ($60.00 vs $80.00 per million) and work measured by AA Intelligence Index or Epoch Capabilities Index, where it leads.
- Shared results
- 5
- GPT-4 only
- 40
- o3 Pro only
- 7
- 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
o3 Pro
o3 Pro leads, 21.9 against 6.7.
Same board, both measured
Long documents
Listed context window
o3 Pro
o3 Pro takes 200K tokens against 8K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
No call
GPT-4 $0.060, o3 Pro $0.060 per turn.
List prices
At a glance
- Coding index
- GPT-4 not benchmarked, o3 Pro not benchmarked.
- Widest category
- Reasoning, 49.6 points apart on average over 1 shared benchmark.
- Widest single gap
- GPQA Diamond (Artificial Analysis run): GPT-4 34.9% against o3 Pro 84.5%, 49.6 points apart on a 0 to 100 scale.
- Output price
- GPT-4 $60.00 against o3 Pro $80.00 per million output tokens, 1.3x apart.
- Context window
- GPT-4 takes 8K tokens, o3 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 | o3 Pro | Ties |
|---|---|---|---|---|
| Intelligence | 0 | 2 | ||
| Reasoning | 0 | 1 | ||
| General | 0 | 2 | ||
| All shared boards | 0 | 5 |
CodingDirectional onlySix of these boards feed the Vibe Coding Index8 boards, none shared
| Benchmark | GPT-4 | o3 Pro | Leader |
|---|---|---|---|
| Aider polyglot | Not measured | 84.9% | Only o3 Pro measured |
| 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 |
| WeirdML | Not measured | 58.2% | Only o3 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 index02
| Benchmark | GPT-4 | o3 Pro | Leader |
|---|---|---|---|
| AA Intelligence Index | 6.7 | 21.9 | o3 Pro |
| Epoch Capabilities Index | 125.7 | 147.3 | o3 Pro |
Agentic workNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-4 | o3 Pro | Leader |
|---|---|---|---|
| Neither model has a result on 41 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GPT-4 | o3 Pro | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 34.9% | 84.5% | o3 Pro |
| ARC-AGI | Not measured | 59.3% | Only o3 Pro measured |
| ARC-AGI-2 | Not measured | 4.9% | Only o3 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 |
| Kagi LLM Benchmark | Not measured | 72.1% | Only o3 Pro measured |
| Neither model has a result on the other 14 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index3 boards, none shared
| Benchmark | GPT-4 | o3 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 | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | GPT-4 | o3 Pro | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 56.2% | Not measured | Only GPT-4 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 | 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 11 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-4 | o3 Pro | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | GPT-4 | o3 Pro | Leader |
|---|---|---|---|
| IFBench | 33.2% | Not measured | Only GPT-4 measured |
| DTBench | 62.7% | 86.9% | o3 Pro |
| LMCA | 17.1% | 38.5% | o3 Pro |
| Fiction.LiveBench | Not measured | 97.2% | Only o3 Pro measured |
| Creative writing (Lech Mazur) | Not measured | 84.4% | Only o3 Pro 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 22 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-4 | o3 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
Same cost
Repository review
50K input + 3K output tokens
o3 Pro costs less
Agent loop
200K input + 10K output tokens
o3 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 | OpenAI o3 Pro |
|---|---|---|
| Maker | OpenAI | OpenAI |
| Weights | No public weights listed | No public weights listed |
| Released | May 28, 2023 | June 10, 2025 |
| Context window | 8K | 200K |
| Input $/Mtok | $30.00 | $20.00 |
| Output $/Mtok | $60.00 | $80.00 |
| 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 o3 Pro for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick GPT-4 for output tokens 1.3x cheaper ($60.00 vs $80.00 per million) and work measured by AA Intelligence Index or Epoch Capabilities Index, where it leads.
Which is cheaper, GPT-4 or o3 Pro?
GPT-4 costs $30.00 per million input tokens and $60.00 per million output tokens; o3 Pro costs $20.00 and $80.00. Cost per solved task is known for neither of them.
Which has the bigger context window, GPT-4 or o3 Pro?
o3 Pro, with 200K tokens against 8K.
How many benchmarks is the GPT-4 vs o3 Pro comparison based on?
5 benchmarks have a result for both models as of October 22, 2026. GPT-4's coding index rests on 0 independent benchmarks and o3 Pro's on 0. Where only one model has a result, the page says so instead of naming a winner.