Gemini 4 Carbon vs GPT-5.2-Codex
Gemini 4 Carbon leads GPT-5.2-Codex on coding, 86.6 to 45.4 on the Vibe Coding Index, and Gemini 4 Carbon costs 1.4x less per output token ($10.00 vs $14.00 per million). Updated November 14, 2026; 7 benchmarks have a result for both.
Gemini 4 Carbon or GPT-5.2-Codex: which to pick
Pick Gemini 4 Carbon for coding: it scores 86.6 on the Vibe Coding Index against 45.4 for GPT-5.2-Codex.
Pick GPT-5.2-Codex for work measured by Long context reasoning (AA-LCR), where it leads.
- Shared results
- 7
- Gemini 4 Carbon only
- 66
- GPT-5.2-Codex only
- 15
- 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
Gemini 4 Carbon
Gemini 4 Carbon scores 86.6 against 45.4.
4 and 3 benchmarks behind the scores
Intelligence
AA Intelligence Index
No call
Only Gemini 4 Carbon has a AA Intelligence Index result, 60.0.
Directional only
Web design
Design Arena: websites
No call
Only Gemini 4 Carbon has a Design Arena: websites result, 1319.
Directional only
General
Vals Index
No call
Only Gemini 4 Carbon has a Vals Index result, 70.5%.
Directional only
Long documents
Listed context window
Gemini 4 Carbon
Gemini 4 Carbon takes 1.05M tokens against 400K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemini 4 Carbon
Gemini 4 Carbon $0.0070, GPT-5.2-Codex $0.0088 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-5.2-Codex has the number, $0.43.
Directional only
At a glance
- Coding index
- Gemini 4 Carbon 86.6 from 4 benchmarks, GPT-5.2-Codex 45.4 from 3 benchmarks.
- Widest category
- Coding, 47.1 points apart on average over 5 shared benchmarks.
- Widest single gap
- LMArena WebDev: Gemini 4 Carbon 1768 against GPT-5.2-Codex 1339, 61.3 points apart on a 0 to 100 scale.
- Output price
- Gemini 4 Carbon $10.00 against GPT-5.2-Codex $14.00 per million output tokens, 1.4x apart.
- Context window
- Gemini 4 Carbon takes 1.05M tokens, GPT-5.2-Codex 400K.
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 | Gemini 4 Carbon | Bars | GPT-5.2-Codex | Ties |
|---|---|---|---|---|
| Coding | 5 | 0 | ||
| Agentic work | 1 | 0 | ||
| General | 0 | 1 | ||
| All shared boards | 6 | 1 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index50
| Benchmark | Gemini 4 Carbon | GPT-5.2-Codex | Leader |
|---|---|---|---|
| SWE-bench Verified | Not measured | 72.8% | Only GPT-5.2-Codex measured |
| SWE-bench Multilingual | Not measured | 66.3% | Only GPT-5.2-Codex measured |
| LiveBench coding | 91.0% | Not measured | Only Gemini 4 Carbon measured |
| LMArena WebDev | 1768 | 1339 | Gemini 4 Carbon |
| LiveCodeBench (Vals AI) | Not measured | 88.0% | Only GPT-5.2-Codex measured |
| SWE-bench Verified (Vals AI) | Not measured | 72.4% | Only GPT-5.2-Codex measured |
| Terminal-Bench 4 (Vals AI) | 63.1% | Not measured | Only Gemini 4 Carbon measured |
| Vibe Code Bench (Vals AI) | 89.1% | 37.9% | Gemini 4 Carbon |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 37.1% | Only GPT-5.2-Codex measured |
| Terminal-Bench 4.0 (Artificial Analysis run) | 65.2% | Not measured | Only Gemini 4 Carbon measured |
| FrontierCode 2.0 | 40.6% | Not measured | Only Gemini 4 Carbon measured |
| Terminal-Bench | Not measured | 66.5% | Only GPT-5.2-Codex measured |
| FrontierSWE | 61.2% | Not measured | Only Gemini 4 Carbon measured |
| ALE-Bench | 2374.7 | 1299.9 | Gemini 4 Carbon |
| LMArena Text: coding | 1564 | Not measured | Only Gemini 4 Carbon measured |
| LMArena Text: software and IT | 1552 | Not measured | Only Gemini 4 Carbon measured |
| LMArena WebDev: React | 1792 | 1329 | Gemini 4 Carbon |
| LMArena WebDev: HTML | 1770 | 1348 | Gemini 4 Carbon |
| Terminal-Bench 2.0 | Not measured | 66.5% | Only GPT-5.2-Codex measured |
| CursorBench 4.0 | 60.4% | Not measured | Only Gemini 4 Carbon measured |
| Neither model has a result on the other 32 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | Gemini 4 Carbon | GPT-5.2-Codex | Leader |
|---|---|---|---|
| AA Intelligence Index | 60.0 | Not measured | Only Gemini 4 Carbon measured |
| Epoch Capabilities Index | 169.8 | Not measured | Only Gemini 4 Carbon measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Gemini 4 Carbon | GPT-5.2-Codex | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | Not measured | 1027 | Only GPT-5.2-Codex measured |
| Design Arena: agents building full-stack apps | Not measured | 967 | Only GPT-5.2-Codex measured |
| Design Arena: agents building mobile apps | 1284 | 1082 | Gemini 4 Carbon |
| Design Arena: agents building Android apps | Not measured | 1176 | Only GPT-5.2-Codex measured |
| Design Arena: agents building Godot games | Not measured | 1142 | Only GPT-5.2-Codex measured |
| Design Arena: spreadsheets | 1224 | Not measured | Only Gemini 4 Carbon measured |
| LiveBench research | 92.5% | Not measured | Only Gemini 4 Carbon measured |
| LiveBench browser | 80.0% | Not measured | Only Gemini 4 Carbon measured |
| LiveBench long agentic | 72.7% | Not measured | Only Gemini 4 Carbon measured |
| Tax Agent Bench (Vals AI) | 51.8% | Not measured | Only Gemini 4 Carbon measured |
| Legal Research Bench (Vals AI) | 55.8% | Not measured | Only Gemini 4 Carbon measured |
| Harvey's Legal Agent Benchmark (Vals AI) | 17.5% | Not measured | Only Gemini 4 Carbon measured |
| τ²-Bench Telecom | Not measured | 92.1% | Only GPT-5.2-Codex measured |
| APEX-Agents | 84.2% | Not measured | Only Gemini 4 Carbon measured |
| Vending-Bench 2 | $16,484 | Not measured | Only Gemini 4 Carbon measured |
| Neither model has a result on the other 29 boards here | |||
ReasoningDirectional onlyPublic boards, shown as published, kept out of the index15 boards, none shared
| Benchmark | Gemini 4 Carbon | GPT-5.2-Codex | Leader |
|---|---|---|---|
| LiveBench reasoning | 90.6% | Not measured | Only Gemini 4 Carbon measured |
| GPQA Diamond (Artificial Analysis run) | Not measured | 89.9% | Only GPT-5.2-Codex measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 35.7% | Only GPT-5.2-Codex measured |
| HLE-Diamond (Artificial Analysis run) | 69.1% | Not measured | Only Gemini 4 Carbon measured |
| CritPt v2, hard subset (Artificial Analysis run) | 69.0% | Not measured | Only Gemini 4 Carbon measured |
| GPQA Diamond (Epoch AI run) | 96.5% | Not measured | Only Gemini 4 Carbon measured |
| ARC-AGI | 98.5% | Not measured | Only Gemini 4 Carbon measured |
| ARC-AGI-2 | 94.2% | Not measured | Only Gemini 4 Carbon measured |
| SimpleBench | 92.6% | Not measured | Only Gemini 4 Carbon measured |
| Chess puzzles | 78.0% | Not measured | Only Gemini 4 Carbon measured |
| Mystery game puzzles | 73.0% | Not measured | Only Gemini 4 Carbon measured |
| EBR-bench | 87.6% | Not measured | Only Gemini 4 Carbon measured |
| LMArena Text: hard prompts | 1551 | Not measured | Only Gemini 4 Carbon measured |
| LMArena Text: expert | 1582 | Not measured | Only Gemini 4 Carbon measured |
| LMArena Text: hard prompts in English | 1545 | Not measured | Only Gemini 4 Carbon measured |
| Neither model has a result on the other 11 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | Gemini 4 Carbon | GPT-5.2-Codex | Leader |
|---|---|---|---|
| OTIS Mock AIME | 100.0% | Not measured | Only Gemini 4 Carbon measured |
| FrontierMath, tiers 1 to 3 | 90.5% | Not measured | Only Gemini 4 Carbon measured |
| FrontierMath, tier 4 | 95.1% | Not measured | Only Gemini 4 Carbon measured |
| LMArena Text: mathematical work | 1538 | Not measured | Only Gemini 4 Carbon measured |
| MathArena | 85.4% | Not measured | Only Gemini 4 Carbon measured |
| Neither model has a result on the other 9 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Gemini 4 Carbon | GPT-5.2-Codex | Leader |
|---|---|---|---|
| AA-Omniscience | 53.5 | Not measured | Only Gemini 4 Carbon measured |
| SimpleQA Verified | 77.7% | Not measured | Only Gemini 4 Carbon measured |
| LMArena Text: science | 1535 | Not measured | Only Gemini 4 Carbon measured |
| LMArena Text: medicine and healthcare | 1525 | Not measured | Only Gemini 4 Carbon measured |
| LMArena Text: legal and government | 1542 | Not measured | Only Gemini 4 Carbon measured |
| LMArena Text: business and finance | 1520 | Not measured | Only Gemini 4 Carbon measured |
| FACTS Benchmark Suite | 78.4% | Not measured | Only Gemini 4 Carbon measured |
| PRBench Legal | 53.3% | Not measured | Only Gemini 4 Carbon measured |
| Neither model has a result on the other 13 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Gemini 4 Carbon | GPT-5.2-Codex | Leader |
|---|---|---|---|
| Design Arena: websites | 1319 | Not measured | Only Gemini 4 Carbon measured |
| Design Arena: UI components | 1357 | Not measured | Only Gemini 4 Carbon measured |
| Design Arena: game dev | 1326 | Not measured | Only Gemini 4 Carbon measured |
| Design Arena: 3D | 1434 | Not measured | Only Gemini 4 Carbon measured |
| Design Arena: all code categories | 1348 | Not measured | Only Gemini 4 Carbon measured |
| LiveBench design | 80.2% | Not measured | Only Gemini 4 Carbon measured |
| Neither model has a result on the other 3 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Gemini 4 Carbon | GPT-5.2-Codex | Leader |
|---|---|---|---|
| Vals Index | 70.5% | Not measured | Only Gemini 4 Carbon measured |
| LiveBench data analysis | 86.5% | Not measured | Only Gemini 4 Carbon measured |
| IFBench | Not measured | 77.6% | Only GPT-5.2-Codex measured |
| Long context reasoning (AA-LCR) | 79.3% | 82.3% | GPT-5.2-Codex |
| GDPval-AA | 1733 | Not measured | Only Gemini 4 Carbon measured |
| Furniture assembly | 77.5% | Not measured | Only Gemini 4 Carbon measured |
| LMArena Text | 1538 | Not measured | Only Gemini 4 Carbon measured |
| LMArena Text: instruction following | 1539 | Not measured | Only Gemini 4 Carbon measured |
| LMArena Text: creative writing | 1533 | Not measured | Only Gemini 4 Carbon measured |
| LMArena Text: English | 1530 | Not measured | Only Gemini 4 Carbon measured |
| LMArena Text: non-English | 1534 | Not measured | Only Gemini 4 Carbon measured |
| LMArena Text: Chinese | 1613 | Not measured | Only Gemini 4 Carbon measured |
| LMArena Text: Russian | 1560 | Not measured | Only Gemini 4 Carbon measured |
| LMArena Text: multi-turn | 1569 | Not measured | Only Gemini 4 Carbon measured |
| LMArena Text: longer queries | 1549 | Not measured | Only Gemini 4 Carbon measured |
| LMArena Text: writing and language | 1542 | Not measured | Only Gemini 4 Carbon measured |
| LMArena Text: entertainment and media | 1527 | Not measured | Only Gemini 4 Carbon measured |
| Neither model has a result on the other 32 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemini 4 Carbon | GPT-5.2-Codex | 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
Gemini 4 Carbon costs less
Repository review
50K input + 3K output tokens
GPT-5.2-Codex costs less
Agent loop
200K input + 10K output tokens
GPT-5.2-Codex 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 | Google Gemini 4 Carbon | OpenAI GPT-5.2-Codex |
|---|---|---|
| Maker | OpenAI | |
| Weights | No public weights listed | No public weights listed |
| Released | November 10, 2026 | January 14, 2026 |
| Context window | 1.05M | 400K |
| Input $/Mtok | $2.00 | $1.75 |
| Output $/Mtok | $10.00 | $14.00 |
| Coding index | 86.6 | 45.4 |
| Independent measurements behind it | 4 | 3 |
| Cost per solved task | Not computable | $0.43 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemini 4 Carbon better than GPT-5.2-Codex for coding?
Pick Gemini 4 Carbon for coding: it scores 86.6 on the Vibe Coding Index against 45.4 for GPT-5.2-Codex. Pick GPT-5.2-Codex for work measured by Long context reasoning (AA-LCR), where it leads.
Which is cheaper, Gemini 4 Carbon or GPT-5.2-Codex?
Gemini 4 Carbon costs $2.00 per million input tokens and $10.00 per million output tokens; GPT-5.2-Codex costs $1.75 and $14.00. Cost per solved task is known for GPT-5.2-Codex only.
Which has the bigger context window, Gemini 4 Carbon or GPT-5.2-Codex?
Gemini 4 Carbon, with 1.05M tokens against 400K.
How many benchmarks is the Gemini 4 Carbon vs GPT-5.2-Codex comparison based on?
7 benchmarks have a result for both models as of November 14, 2026. Gemini 4 Carbon's coding index rests on 4 independent benchmarks and GPT-5.2-Codex's on 3. Where only one model has a result, the page says so instead of naming a winner.