Gemma 4 26B A4B vs GPT-5.1-Codex-Mini
GPT-5.1-Codex-Mini leads Gemma 4 26B A4B on the Artificial Analysis Intelligence Index, 20.4 to 16.7, and Gemma 4 26B A4B costs 3.3x less per output token ($0.60 vs $2.00 per million). Updated October 21, 2026; 9 benchmarks have a result for both.
Gemma 4 26B A4B or GPT-5.1-Codex-Mini: which to pick
Neither model has a coding score yet, so the two cannot be ranked on coding.
Pick Gemma 4 26B A4B for output tokens 3.3x cheaper ($0.60 vs $2.00 per million) and work measured by Terminal-Bench Hard (Artificial Analysis run) or AA Intelligence Index, where it leads.
- Shared results
- 9
- Gemma 4 26B A4B only
- 46
- GPT-5.1-Codex-Mini only
- 13
- 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
Neither has a coding score yet.
One side not measured
Intelligence
AA Intelligence Index
GPT-5.1-Codex-Mini
GPT-5.1-Codex-Mini leads, 20.4 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
Web design
Design Arena: websites
No call
Only GPT-5.1-Codex-Mini has a Design Arena: websites result, 1111.
Directional only
Long documents
Listed context window
GPT-5.1-Codex-Mini
GPT-5.1-Codex-Mini 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-5.1-Codex-Mini $0.0013 per turn.
List prices
At a glance
- Coding index
- Gemma 4 26B A4B not benchmarked, GPT-5.1-Codex-Mini not benchmarked.
- Widest category
- Agentic work, 19.3 points apart on average over 1 shared benchmark.
- Widest single gap
- τ²-Bench Telecom: Gemma 4 26B A4B 43.6% against GPT-5.1-Codex-Mini 62.9%, 19.3 points apart on a 0 to 100 scale.
- Output price
- Gemma 4 26B A4B $0.60 against GPT-5.1-Codex-Mini $2.00 per million output tokens, 3.3x apart.
- Context window
- Gemma 4 26B A4B takes 262K tokens, GPT-5.1-Codex-Mini 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-5.1-Codex-Mini | Ties |
|---|---|---|---|---|
| Coding | 2 | 1 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 0 | 1 | ||
| Reasoning | 1 | 1 | ||
| General | 1 | 1 | ||
| All shared boards | 4 | 5 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index21
| Benchmark | Gemma 4 26B A4B | GPT-5.1-Codex-Mini | Leader |
|---|---|---|---|
| LMArena WebDev | 1360 | 1244 | Gemma 4 26B A4B |
| AA Coding Index | 39.3 | Not measured | Only Gemma 4 26B A4B measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 83.6% | Only GPT-5.1-Codex-Mini measured |
| SciCode | 40.0% | Not measured | Only Gemma 4 26B A4B measured |
| Terminal-Bench Hard (Artificial Analysis run) | 25.0% | 33.3% | GPT-5.1-Codex-Mini |
| Terminal-Bench | Not measured | 61.6% | Only GPT-5.1-Codex-Mini measured |
| WeirdML | 35.2% | Not measured | Only Gemma 4 26B A4B measured |
| ALE-Bench | 927.2 | Not measured | Only Gemma 4 26B A4B measured |
| 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 | Not measured | Only Gemma 4 26B A4B measured |
| LMArena WebDev: HTML | 1362 | 1253 | Gemma 4 26B A4B |
| Neither model has a result on the other 27 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Gemma 4 26B A4B | GPT-5.1-Codex-Mini | Leader |
|---|---|---|---|
| AA Intelligence Index | 16.7 | 20.4 | GPT-5.1-Codex-Mini |
| 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-5.1-Codex-Mini | Leader |
|---|---|---|---|
| AA Agentic Index | 2.9 | Not measured | Only Gemma 4 26B A4B measured |
| τ²-Bench Telecom | 43.6% | 62.9% | GPT-5.1-Codex-Mini |
| Neither model has a result on the other 39 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | Gemma 4 26B A4B | GPT-5.1-Codex-Mini | Leader |
|---|---|---|---|
| GPQA Diamond (Artificial Analysis run) | 79.2% | 81.3% | GPT-5.1-Codex-Mini |
| Humanity's Last Exam (Artificial Analysis run) | 19.3% | 18.5% | Gemma 4 26B A4B |
| 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 index5 boards, none shared
| Benchmark | Gemma 4 26B A4B | GPT-5.1-Codex-Mini | Leader |
|---|---|---|---|
| AA Math Index | Not measured | 91.7 | Only GPT-5.1-Codex-Mini measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 91.7% | Only GPT-5.1-Codex-Mini measured |
| 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 8 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index6 boards, none shared
| Benchmark | Gemma 4 26B A4B | GPT-5.1-Codex-Mini | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | Not measured | 82.0% | Only GPT-5.1-Codex-Mini measured |
| 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 12 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index8 boards, none shared
| Benchmark | Gemma 4 26B A4B | GPT-5.1-Codex-Mini | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1111 | Only GPT-5.1-Codex-Mini measured |
| Design Arena: UI components | Not measured | 1081 | Only GPT-5.1-Codex-Mini measured |
| Design Arena: game dev | Not measured | 1092 | Only GPT-5.1-Codex-Mini measured |
| Design Arena: data viz | Not measured | 1097 | Only GPT-5.1-Codex-Mini measured |
| Design Arena: 3D | Not measured | 988 | Only GPT-5.1-Codex-Mini measured |
| Design Arena: all code categories | Not measured | 1094 | Only GPT-5.1-Codex-Mini measured |
| Design Arena: SVG | Not measured | 978 | Only GPT-5.1-Codex-Mini measured |
| Design Arena: ASCII art | Not measured | 1105 | Only GPT-5.1-Codex-Mini measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index11
| Benchmark | Gemma 4 26B A4B | GPT-5.1-Codex-Mini | Leader |
|---|---|---|---|
| IFBench | 72.4% | 67.9% | Gemma 4 26B A4B |
| Long context reasoning (AA-LCR) | 65.7% | 66.7% | GPT-5.1-Codex-Mini |
| 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-5.1-Codex-Mini | 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-5.1-Codex-Mini |
|---|---|---|
| Maker | OpenAI | |
| Weights | Open weights | No public weights listed |
| Released | April 3, 2026 | November 13, 2025 |
| Context window | 262K | 400K |
| Input $/Mtok | $0.15 | $0.25 |
| Output $/Mtok | $0.60 | $2.00 |
| Coding index | Not benchmarked | Not benchmarked |
| Independent measurements behind it | 1 | 1 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemma 4 26B A4B better than GPT-5.1-Codex-Mini for coding?
Neither model has a coding score yet, so the two cannot be ranked on coding. Pick Gemma 4 26B A4B for output tokens 3.3x cheaper ($0.60 vs $2.00 per million) and work measured by Terminal-Bench Hard (Artificial Analysis run) or AA Intelligence Index, where it leads.
Which is cheaper, Gemma 4 26B A4B or GPT-5.1-Codex-Mini?
Gemma 4 26B A4B costs $0.15 per million input tokens and $0.60 per million output tokens; GPT-5.1-Codex-Mini costs $0.25 and $2.00. Cost per solved task is known for neither of them.
Which has the bigger context window, Gemma 4 26B A4B or GPT-5.1-Codex-Mini?
GPT-5.1-Codex-Mini, with 400K tokens against 262K.
How many benchmarks is the Gemma 4 26B A4B vs GPT-5.1-Codex-Mini comparison based on?
9 benchmarks have a result for both models as of October 21, 2026. Gemma 4 26B A4B's coding index rests on 1 independent benchmark and GPT-5.1-Codex-Mini's on 1. Where only one model has a result, the page says so instead of naming a winner.