Gemma 4 26B A4B vs GPT-6 Luna
GPT-6 Luna leads Gemma 4 26B A4B on the Artificial Analysis Intelligence Index, 38.1 to 16.7, and GPT-6 Luna costs 1.2x less per output token ($0.50 vs $0.60 per million). Updated October 22, 2026; 45 benchmarks have a result for both.
Gemma 4 26B A4B or GPT-6 Luna: which to pick
Only GPT-6 Luna has a coding score, 57.3 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 work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.
- Shared results
- 45
- Gemma 4 26B A4B only
- 10
- GPT-6 Luna only
- 58
- Like-for-like categories
- 6 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-6 Luna has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
GPT-6 Luna
GPT-6 Luna leads, 38.1 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-6 Luna has a Design Arena: websites result, 1271.
Directional only
General
Vals Index
No call
Only GPT-6 Luna has a Vals Index result, 52.3%.
Directional only
Long documents
Listed context window
GPT-6 Luna
GPT-6 Luna takes 1.05M tokens against 262K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
GPT-6 Luna
Gemma 4 26B A4B $0.0004, GPT-6 Luna $0.0003 per turn.
List prices
At a glance
- Coding index
- Gemma 4 26B A4B not benchmarked, GPT-6 Luna 57.3 from 5 benchmarks.
- Widest category
- Coding, 21.4 points apart on average over 7 shared benchmarks.
- Widest single gap
- LMArena WebDev: HTML: Gemma 4 26B A4B 1362 against GPT-6 Luna 1595, 38.9 points apart on a 0 to 100 scale.
- Output price
- Gemma 4 26B A4B $0.60 against GPT-6 Luna $0.50 per million output tokens, 1.2x apart.
- Context window
- Gemma 4 26B A4B takes 262K tokens, GPT-6 Luna 1.05M.
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-6 Luna | Ties |
|---|---|---|---|---|
| Coding | 2 | 5 | ||
| Intelligence | 0 | 2 | ||
| Reasoning | 5 | 2 | ||
| Math | 2 | 1 | ||
| Knowledge | 4 | 1 | ||
| General | 18 | 3 | ||
| All shared boards | 31 | 14 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index25
| Benchmark | Gemma 4 26B A4B | GPT-6 Luna | Leader |
|---|---|---|---|
| LiveBench coding | Not measured | 84.5% | Only GPT-6 Luna measured |
| LMArena WebDev | 1360 | 1578 | GPT-6 Luna |
| AA Coding Index | 39.3 | Not measured | Only Gemma 4 26B A4B measured |
| Terminal-Bench 4 (Vals AI) | Not measured | 13.6% | Only GPT-6 Luna measured |
| Vibe Code Bench (Vals AI) | Not measured | 81.7% | Only GPT-6 Luna measured |
| Code migration (Vals AI) | Not measured | 42.5% | Only GPT-6 Luna measured |
| ProgramBench (Vals AI) | Not measured | 0.5% | Only GPT-6 Luna measured |
| IOI (Vals AI) | Not measured | 55.6% | Only GPT-6 Luna measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 73.0% | Only GPT-6 Luna measured |
| SWE-bench Multimodal (Vals AI) | Not measured | 37.5% | Only GPT-6 Luna measured |
| CyberBench (Vals AI) | Not measured | 76.3% | Only GPT-6 Luna measured |
| SciCode | 40.0% | 54.6% | GPT-6 Luna |
| Terminal-Bench Hard (Artificial Analysis run) | 25.0% | Not measured | Only Gemma 4 26B A4B measured |
| FrontierCode | Not measured | 42.4% | Only GPT-6 Luna measured |
| WeirdML | 35.2% | Not measured | Only Gemma 4 26B A4B measured |
| ALE-Bench | 927.2 | 1576.9 | GPT-6 Luna |
| LMArena Text: coding | 1446 | 1437 | Gemma 4 26B A4B |
| LMArena Text: software and IT | 1454 | 1423 | Gemma 4 26B A4B |
| LMArena WebDev: React | 1351 | 1573 | GPT-6 Luna |
| LMArena WebDev: HTML | 1362 | 1595 | GPT-6 Luna |
| LMArena WebDev: from an image | Not measured | 1571 | Only GPT-6 Luna measured |
| Neither model has a result on the other 18 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | Gemma 4 26B A4B | GPT-6 Luna | Leader |
|---|---|---|---|
| AA Intelligence Index | 16.7 | 38.1 | GPT-6 Luna |
| Epoch Capabilities Index | 141.9 | 156.8 | GPT-6 Luna |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index19 boards, none shared
| Benchmark | Gemma 4 26B A4B | GPT-6 Luna | Leader |
|---|---|---|---|
| AA Agentic Index | 2.9 | Not measured | Only Gemma 4 26B A4B measured |
| Design Arena: agents building web apps | Not measured | 1191 | Only GPT-6 Luna measured |
| Design Arena: agents building full-stack apps | Not measured | 1158 | Only GPT-6 Luna measured |
| Design Arena: agents building mobile apps | Not measured | 1134 | Only GPT-6 Luna measured |
| LiveBench research | Not measured | 43.5% | Only GPT-6 Luna measured |
| LiveBench browser | Not measured | 72.0% | Only GPT-6 Luna measured |
| LiveBench long agentic | Not measured | 48.1% | Only GPT-6 Luna measured |
| SREBench (Vals AI) | Not measured | 2.7% | Only GPT-6 Luna measured |
| Finance Agent (Vals AI) | Not measured | 49.9% | Only GPT-6 Luna measured |
| Tax Agent Bench (Vals AI) | Not measured | 19.9% | Only GPT-6 Luna measured |
| Legal Research Bench (Vals AI) | Not measured | 30.3% | Only GPT-6 Luna measured |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 4.2% | Only GPT-6 Luna measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 68.5% | Only GPT-6 Luna measured |
| BioMysteryBench (Vals AI) | Not measured | 61.5% | Only GPT-6 Luna measured |
| Terminal-Bench-Science (Vals AI) | Not measured | 4.3% | Only GPT-6 Luna measured |
| Vals Science Index | Not measured | 28.4% | Only GPT-6 Luna measured |
| τ²-Bench Telecom | 43.6% | Not measured | Only Gemma 4 26B A4B measured |
| APEX-Agents | Not measured | 44.3% | Only GPT-6 Luna measured |
| SpireClimb | Not measured | 0.0% | Only GPT-6 Luna measured |
| Neither model has a result on the other 22 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index52
| Benchmark | Gemma 4 26B A4B | GPT-6 Luna | Leader |
|---|---|---|---|
| LiveBench reasoning | Not measured | 81.8% | Only GPT-6 Luna measured |
| MysteryMechanism (Vals AI) | Not measured | 19.4% | Only GPT-6 Luna measured |
| GPQA Diamond (Artificial Analysis run) | 79.2% | Not measured | Only Gemma 4 26B A4B measured |
| Humanity's Last Exam (Artificial Analysis run) | 19.3% | 38.5% | GPT-6 Luna |
| GPQA Diamond (Epoch AI run) | 73.2% | 90.5% | GPT-6 Luna |
| ARC-AGI | Not measured | 86.7% | Only GPT-6 Luna measured |
| ARC-AGI-2 | Not measured | 59.3% | Only GPT-6 Luna measured |
| Chess puzzles | Not measured | 36.0% | Only GPT-6 Luna measured |
| Mystery game puzzles | Not measured | 7.0% | Only GPT-6 Luna measured |
| LMArena Text: hard prompts | 1438 | 1410 | Gemma 4 26B A4B |
| LMArena Text: expert | 1447 | 1442 | Gemma 4 26B A4B |
| LMArena Text: hard prompts in English | 1448 | 1410 | Gemma 4 26B A4B |
| LMArena Vision: diagrams | 1264 | 1245 | Gemma 4 26B A4B |
| LMArena Vision: homework | 1293 | 1261 | Gemma 4 26B A4B |
| Neither model has a result on the other 8 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index21
| Benchmark | Gemma 4 26B A4B | GPT-6 Luna | Leader |
|---|---|---|---|
| OTIS Mock AIME | 82.2% | 98.9% | GPT-6 Luna |
| FrontierMath, tiers 1 to 3 | Not measured | 78.9% | Only GPT-6 Luna measured |
| FrontierMath, tier 4 | Not measured | 56.1% | Only GPT-6 Luna measured |
| ProofBench | Not measured | 64.0% | Only GPT-6 Luna measured |
| LMArena Text: math | 1470 | 1409 | Gemma 4 26B A4B |
| LMArena Text: mathematical work | 1475 | 1427 | Gemma 4 26B A4B |
| Neither model has a result on the other 7 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index41
| Benchmark | Gemma 4 26B A4B | GPT-6 Luna | Leader |
|---|---|---|---|
| MedCode (Vals AI) | Not measured | 44.7% | Only GPT-6 Luna measured |
| SimpleQA Verified | Not measured | 41.4% | Only GPT-6 Luna measured |
| LMArena Text: science | 1446 | 1386 | Gemma 4 26B A4B |
| LMArena Text: medicine and healthcare | 1428 | 1352 | Gemma 4 26B A4B |
| LMArena Text: legal and government | 1457 | 1400 | Gemma 4 26B A4B |
| LMArena Text: business and finance | 1429 | 1388 | Gemma 4 26B A4B |
| FACTS Benchmark Suite | 42.7% | 63.3% | GPT-6 Luna |
| Neither model has a result on the other 11 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | Gemma 4 26B A4B | GPT-6 Luna | Leader |
|---|---|---|---|
| Design Arena: websites | Not measured | 1271 | Only GPT-6 Luna measured |
| Design Arena: UI components | Not measured | 1295 | Only GPT-6 Luna measured |
| Design Arena: game dev | Not measured | 1257 | Only GPT-6 Luna measured |
| Design Arena: data viz | Not measured | 1216 | Only GPT-6 Luna measured |
| Design Arena: 3D | Not measured | 1218 | Only GPT-6 Luna measured |
| Design Arena: all code categories | Not measured | 1270 | Only GPT-6 Luna measured |
| Design Arena: SVG | Not measured | 1252 | Only GPT-6 Luna measured |
| Design Arena: ASCII art | Not measured | 1153 | Only GPT-6 Luna measured |
| LiveBench design | Not measured | 82.5% | Only GPT-6 Luna measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index183
| Benchmark | Gemma 4 26B A4B | GPT-6 Luna | Leader |
|---|---|---|---|
| Vals Index | Not measured | 52.3% | Only GPT-6 Luna measured |
| LiveBench data analysis | Not measured | 73.4% | Only GPT-6 Luna measured |
| Public Benefits Bench (Vals AI) | Not measured | 57.6% | Only GPT-6 Luna measured |
| SAGE (Vals AI) | Not measured | 48.1% | Only GPT-6 Luna measured |
| MedScribe (Vals AI) | Not measured | 83.7% | Only GPT-6 Luna measured |
| IFBench | 72.4% | Not measured | Only Gemma 4 26B A4B measured |
| Long context reasoning (AA-LCR) | 65.7% | 83.3% | GPT-6 Luna |
| DTBench | 74.9% | 90.1% | GPT-6 Luna |
| LMCA | 29.7% | 44.5% | GPT-6 Luna |
| Furniture assembly | Not measured | 44.2% | Only GPT-6 Luna measured |
| LMArena Text | 1434 | 1389 | Gemma 4 26B A4B |
| LMArena Text: instruction following | 1420 | 1408 | Gemma 4 26B A4B |
| LMArena Text: creative writing | 1400 | 1363 | Gemma 4 26B A4B |
| LMArena Vision | 1260 | 1216 | Gemma 4 26B A4B |
| LMArena Text: English | 1444 | 1393 | Gemma 4 26B A4B |
| LMArena Text: non-English | 1421 | 1381 | Gemma 4 26B A4B |
| LMArena Text: Chinese | 1495 | 1427 | Gemma 4 26B A4B |
| LMArena Text: German | Not measured | 1376 | Only GPT-6 Luna measured |
| LMArena Text: Japanese | Not measured | 1369 | Only GPT-6 Luna measured |
| LMArena Text: Korean | Not measured | 1359 | Only GPT-6 Luna measured |
| LMArena Text: French | 1460 | 1408 | Gemma 4 26B A4B |
| LMArena Text: Spanish | 1415 | 1391 | Gemma 4 26B A4B |
| LMArena Text: Russian | 1434 | 1392 | Gemma 4 26B A4B |
| LMArena Text: Polish | Not measured | 1383 | Only GPT-6 Luna measured |
| LMArena Text: multi-turn | 1441 | 1392 | Gemma 4 26B A4B |
| LMArena Text: longer queries | 1427 | 1408 | Gemma 4 26B A4B |
| LMArena Text: writing and language | 1405 | 1384 | Gemma 4 26B A4B |
| LMArena Text: entertainment and media | 1403 | 1364 | Gemma 4 26B A4B |
| LMArena Vision: English | 1256 | 1204 | Gemma 4 26B A4B |
| LMArena Vision: Chinese | 1312 | 1266 | Gemma 4 26B A4B |
| LMArena Vision: reading text | 1268 | 1225 | Gemma 4 26B A4B |
| 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 | 1205 | Gemma 4 26B A4B |
| Neither model has a result on the other 11 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemma 4 26B A4B | GPT-6 Luna | 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-6 Luna costs less
Repository review
50K input + 3K output tokens
GPT-6 Luna costs less
Agent loop
200K input + 10K output tokens
GPT-6 Luna 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-6 Luna |
|---|---|---|
| Maker | OpenAI | |
| Weights | Open weights | No public weights listed |
| Released | April 3, 2026 | September 22, 2026 |
| Context window | 262K | 1.05M |
| Input $/Mtok | $0.15 | $0.10 |
| Output $/Mtok | $0.60 | $0.50 |
| Coding index | Not benchmarked | 57.3 |
| Independent measurements behind it | 1 | 5 |
| Cost per solved task | Not computable | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemma 4 26B A4B better than GPT-6 Luna for coding?
Only GPT-6 Luna has a coding score, 57.3 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 work measured by LMArena Text: coding or LMArena Text: software and IT, where it leads.
Which is cheaper, Gemma 4 26B A4B or GPT-6 Luna?
Gemma 4 26B A4B costs $0.15 per million input tokens and $0.60 per million output tokens; GPT-6 Luna costs $0.10 and $0.50. Cost per solved task is known for neither of them.
Which has the bigger context window, Gemma 4 26B A4B or GPT-6 Luna?
GPT-6 Luna, with 1.05M tokens against 262K.
How many benchmarks is the Gemma 4 26B A4B vs GPT-6 Luna comparison based on?
45 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-6 Luna's on 5. Where only one model has a result, the page says so instead of naming a winner.