Gemma 4 26B A4B vs GPT-5.2-Codex
GPT-5.2-Codex leads Gemma 4 26B A4B on the Artificial Analysis Intelligence Index, 28.5 to 16.7, and Gemma 4 26B A4B costs 23.3x less per output token ($0.60 vs $14.00 per million). Updated October 22, 2026; 11 benchmarks have a result for both.
Gemma 4 26B A4B or GPT-5.2-Codex: which to pick
Only GPT-5.2-Codex has a coding score, 45.4 on the Vibe Coding Index; Gemma 4 26B A4B has none, so the two cannot be ranked on coding.
Pick Gemma 4 26B A4B for output tokens 23.3x cheaper ($0.60 vs $14.00 per million) and work measured by LMArena WebDev or LMArena WebDev: React, where it leads.
- Shared results
- 11
- Gemma 4 26B A4B only
- 44
- GPT-5.2-Codex only
- 11
- Like-for-like categories
- 5 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-5.2-Codex has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
GPT-5.2-Codex
GPT-5.2-Codex leads, 28.5 against 16.7.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Gemma 4 26B A4B has a AA Agentic Index result, 2.9.
Directional only
Long documents
Listed context window
GPT-5.2-Codex
GPT-5.2-Codex takes 400K tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemma 4 26B A4B
Gemma 4 26B A4B $0.0004, 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
- Gemma 4 26B A4B not benchmarked, GPT-5.2-Codex 45.4 from 3 benchmarks.
- Widest category
- Agentic work, 48.5 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: Gemma 4 26B A4B 43.6% against GPT-5.2-Codex 92.1%, 48.5 points apart on a 0 to 100 scale.
- Output price
- Gemma 4 26B A4B $0.60 against GPT-5.2-Codex $14.00 per million output tokens, 23.3x apart.
- Context window
- Gemma 4 26B A4B takes 262K 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 | Gemma 4 26B A4B | Bars | GPT-5.2-Codex | Ties |
|---|---|---|---|---|
| Coding | 3 | 2 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 0 | 2 | ||
| General | 0 | 2 | ||
| All shared boards | 3 | 8 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index32
| Benchmark | Gemma 4 26B A4B | 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 |
| LMArena WebDev | 1360 | 1339 | Gemma 4 26B A4B |
| AA Coding Index | 39.3 | Not measured | Only Gemma 4 26B A4B measured |
| 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 |
| Vibe Code Bench (Vals AI) | Not measured | 37.9% | Only GPT-5.2-Codex measured |
| SciCode | 40.0% | Not measured | Only Gemma 4 26B A4B measured |
| Terminal-Bench Hard (Artificial Analysis run) | 25.0% | 37.1% | GPT-5.2-Codex |
| Terminal-Bench | Not measured | 66.5% | Only GPT-5.2-Codex measured |
| WeirdML | 35.2% | Not measured | Only Gemma 4 26B A4B measured |
| ALE-Bench | 927.2 | 1299.9 | GPT-5.2-Codex |
| LMArena Text: coding | 1446 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Text: software and IT | 1454 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena WebDev: React | 1351 | 1329 | Gemma 4 26B A4B |
| LMArena WebDev: HTML | 1362 | 1348 | Gemma 4 26B A4B |
| Neither model has a result on the other 23 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Gemma 4 26B A4B | GPT-5.2-Codex | Leader |
|---|---|---|---|
| AA Intelligence Index | 16.7 | 28.5 | GPT-5.2-Codex |
| Epoch Capabilities Index | 141.9 | Not measured | Only Gemma 4 26B A4B measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Gemma 4 26B A4B | GPT-5.2-Codex | Leader |
|---|---|---|---|
| AA Agentic Index | 2.9 | Not measured | Only Gemma 4 26B A4B measured |
| Design Arena: agents building web apps | Not measured | 1051 | Only GPT-5.2-Codex measured |
| Design Arena: agents building full-stack apps | Not measured | 993 | Only GPT-5.2-Codex measured |
| Design Arena: agents building mobile apps | Not measured | 1090 | Only GPT-5.2-Codex measured |
| 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 |
| τ²-Bench Telecom | 43.6% | 92.1% | GPT-5.2-Codex |
| Neither model has a result on the other 34 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Gemma 4 26B A4B | GPT-5.2-Codex | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 79.2% | 89.9% | GPT-5.2-Codex |
| Humanity's Last Exam (Artificial Analysis run) | 19.3% | 35.7% | GPT-5.2-Codex |
| GPQA Diamond (Epoch AI run) | 73.2% | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Text: hard prompts | 1438 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Text: expert | 1447 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Text: hard prompts in English | 1448 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Vision: diagrams | 1264 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Vision: homework | 1293 | Not measured | Only Gemma 4 26B A4B 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 | Gemma 4 26B A4B | GPT-5.2-Codex | Leader |
|---|---|---|---|
| OTIS Mock AIME | 82.2% | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Text: math | 1470 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Text: mathematical work | 1475 | Not measured | Only Gemma 4 26B A4B measured |
| Neither model has a result on the other 10 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index5 boards, none shared
| Benchmark | Gemma 4 26B A4B | GPT-5.2-Codex | Leader |
|---|---|---|---|
| LMArena Text: science | 1446 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Text: medicine and healthcare | 1428 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Text: legal and government | 1457 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Text: business and finance | 1429 | Not measured | Only Gemma 4 26B A4B measured |
| FACTS Benchmark Suite | 42.7% | Not measured | Only Gemma 4 26B A4B measured |
| Neither model has a result on the other 13 boards here | |||
Web designNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemma 4 26B A4B | GPT-5.2-Codex | Leader |
|---|---|---|---|
| Neither model has a result on 9 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Gemma 4 26B A4B | GPT-5.2-Codex | Leader |
|---|---|---|---|
| IFBench | 72.4% | 77.6% | GPT-5.2-Codex |
| Long context reasoning (AA-LCR) | 65.7% | 82.3% | GPT-5.2-Codex |
| DTBench | 74.9% | Not measured | Only Gemma 4 26B A4B measured |
| LMCA | 29.7% | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Text | 1434 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Text: instruction following | 1420 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Text: creative writing | 1400 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Vision | 1260 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Text: English | 1444 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Text: non-English | 1421 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Text: Chinese | 1495 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Text: French | 1460 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Text: Spanish | 1415 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Text: Russian | 1434 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Text: multi-turn | 1441 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Text: longer queries | 1427 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Text: writing and language | 1405 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Text: entertainment and media | 1403 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Vision: English | 1256 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Vision: Chinese | 1312 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Vision: reading text | 1268 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Vision: humor | 1272 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Vision: captioning | 1297 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Vision: recognizing things | 1191 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena Vision: creative writing | 1256 | Not measured | Only Gemma 4 26B A4B measured |
| Neither model has a result on the other 21 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemma 4 26B A4B | 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
Gemma 4 26B A4B costs less
Repository review
50K input + 3K output tokens
Gemma 4 26B A4B costs less
Agent loop
200K input + 10K output tokens
Gemma 4 26B A4B 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 Gemma 4 26B A4B | OpenAI GPT-5.2-Codex |
|---|---|---|
| Maker | OpenAI | |
| Weights | Open weights | No public weights listed |
| Released | April 3, 2026 | January 14, 2026 |
| Context window | 262K | 400K |
| Input $/Mtok | $0.15 | $1.75 |
| Output $/Mtok | $0.60 | $14.00 |
| Coding index | Not benchmarked | 45.4 |
| Independent measurements behind it | 1 | 3 |
| Cost per solved task | Not computable | $0.43 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemma 4 26B A4B better than GPT-5.2-Codex for coding?
Only GPT-5.2-Codex has a coding score, 45.4 on the Vibe Coding Index; Gemma 4 26B A4B has none, so the two cannot be ranked on coding. Pick Gemma 4 26B A4B for output tokens 23.3x cheaper ($0.60 vs $14.00 per million) and work measured by LMArena WebDev or LMArena WebDev: React, where it leads.
Which is cheaper, Gemma 4 26B A4B or GPT-5.2-Codex?
Gemma 4 26B A4B costs $0.15 per million input tokens and $0.60 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, Gemma 4 26B A4B or GPT-5.2-Codex?
GPT-5.2-Codex, with 400K tokens against 262K.
How many benchmarks is the Gemma 4 26B A4B vs GPT-5.2-Codex comparison based on?
11 benchmarks have a result for both models as of October 22, 2026. Gemma 4 26B A4B's coding index rests on 1 independent benchmark and GPT-5.2-Codex's on 3. Where only one model has a result, the page says so instead of naming a winner.