Claude Opus 4.8 vs Gemma 3 27B
Updated October 21, 2026. 51 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
vs boards won of 51 shared
Decision reading
Pick Claude Opus 4.8 for coding: it scores 66.0 on the Vibe Coding Index against 4.9 for Gemma 3 27B.
Pick Gemma 3 27B when output tokens cost 71.4x less.
Model AClaude Opus 4.8Anthropic66.0/1002 independent benchmarks$2.17 per solved taskModel BGemma 3 27BGoogle4.9/1001 independent benchmarkNo cost per solved task
- Shared results
- 51
- Claude Opus 4.8 only
- 75
- Gemma 3 27B only
- 11
- Like-for-like categories
- 7 of 9
Shared results can support a head-to-head reading. Results only one model has describe coverage, not superiority.
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, four public coding benchmarks
Claude Opus 4.8
Claude Opus 4.8 scores 66.0 against 4.9.
2 and 1 benchmarks behind the scores
Intelligence
AA Intelligence Index
Claude Opus 4.8
Claude Opus 4.8 leads, 41.8 against 4.9.
Same board, both measured
Agentic work
AA Agentic Index
Claude Opus 4.8
Claude Opus 4.8 leads, 41.9 against 0.1.
Same board, both measured
Reasoning
GPQA Diamond
No call
Only Claude Opus 4.8 has a GPQA Diamond result, 92.4%.
Directional only
Knowledge
MMLU Pro
No call
Only Claude Opus 4.8 has a MMLU Pro result, 89.6%.
Directional only
Web design
Design Arena: websites
No call
Only Claude Opus 4.8 has a Design Arena: websites result, 1258.
Directional only
Long documents
Listed context window
Claude Opus 4.8
Claude Opus 4.8 takes 1M tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemma 3 27B
Claude Opus 4.8 $0.018, Gemma 3 27B $0.0003 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Claude Opus 4.8 has the number, $2.17.
Directional only
At a glance
- Coding index
- Claude Opus 4.8 66.0 from 2 benchmarks, Gemma 3 27B 4.9 from 1 benchmark.
- Widest category
- Agentic work, 62.9 points apart on average over 2 shared benchmarks.
- Widest single gap
- τ²-Bench Telecom: Claude Opus 4.8 94.4% against Gemma 3 27B 10.5%, 83.9 points apart on a 0 to 100 scale.
- Output price
- Claude Opus 4.8 $25.00 against Gemma 3 27B $0.35 per million output tokens, 71.4x apart.
- Context window
- Claude Opus 4.8 takes 1M tokens, Gemma 3 27B 131K.
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 | Claude Opus 4.8 | Bars | Gemma 3 27B | Ties |
|---|---|---|---|---|
| Coding | 5 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 2 | 0 | ||
| Reasoning | 8 | 0 | ||
| Math | 3 | 0 | ||
| Knowledge | 4 | 0 | ||
| General | 27 | 0 | ||
| All shared boards | 51 | 0 |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index50
| Benchmark | Claude Opus 4.8 | Gemma 3 27B | Leader |
|---|---|---|---|
| Aider polyglot | Not measured | 4.9% | Only Gemma 3 27B measured |
| LiveBench coding | 77.3% | Not measured | Only Claude Opus 4.8 measured |
| LMArena WebDev | 1556 | Not measured | Only Claude Opus 4.8 measured |
| AA Coding Index | 74.3 | 10.1 | Claude Opus 4.8 |
| LiveCodeBench (Vals AI) | 87.8% | Not measured | Only Claude Opus 4.8 measured |
| SWE-bench Verified (Vals AI) | 88.6% | Not measured | Only Claude Opus 4.8 measured |
| Terminal-Bench 4 (Vals AI) | 23.2% | Not measured | Only Claude Opus 4.8 measured |
| Vibe Code Bench (Vals AI) | 82.7% | Not measured | Only Claude Opus 4.8 measured |
| Code migration (Vals AI) | 47.3% | Not measured | Only Claude Opus 4.8 measured |
| ProgramBench (Vals AI) | 1.0% | Not measured | Only Claude Opus 4.8 measured |
| Terminal-Bench 2.1 (Vals AI) | 71.9% | Not measured | Only Claude Opus 4.8 measured |
| SkillsBench (Vals AI) | 59.2% | Not measured | Only Claude Opus 4.8 measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 13.7% | Only Gemma 3 27B measured |
| SciCode | 54.4% | 23.3% | Claude Opus 4.8 |
| Terminal-Bench Hard (Artificial Analysis run) | 58.3% | 3.8% | Claude Opus 4.8 |
| FrontierCode | 46.5% | Not measured | Only Claude Opus 4.8 measured |
| GSO-Bench | 47.1% | Not measured | Only Claude Opus 4.8 measured |
| WeirdML | 82.9% | Not measured | Only Claude Opus 4.8 measured |
| LMArena Text: coding | 1490 | 1322 | Claude Opus 4.8 |
| LMArena Text: software and IT | 1488 | 1354 | Claude Opus 4.8 |
| LMArena WebDev: React | 1557 | Not measured | Only Claude Opus 4.8 measured |
| LMArena WebDev: HTML | 1543 | Not measured | Only Claude Opus 4.8 measured |
| Neither model has a result on the other 16 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Opus 4.8 | Gemma 3 27B | Leader |
|---|---|---|---|
| AA Intelligence Index | 41.8 | 4.9 | Claude Opus 4.8 |
| Epoch Capabilities Index | 159.0 | 130.0 | Claude Opus 4.8 |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Claude Opus 4.8 | Gemma 3 27B | Leader |
|---|---|---|---|
| AA Agentic Index | 41.9 | 0.1 | Claude Opus 4.8 |
| Design Arena: agents building web apps | 1233 | Not measured | Only Claude Opus 4.8 measured |
| Design Arena: agents building full-stack apps | 1249 | Not measured | Only Claude Opus 4.8 measured |
| Design Arena: agents building mobile apps | 1222 | Not measured | Only Claude Opus 4.8 measured |
| Design Arena: agents building Android apps | 1237 | Not measured | Only Claude Opus 4.8 measured |
| Design Arena: agents building Godot games | 1231 | Not measured | Only Claude Opus 4.8 measured |
| Design Arena: agents building games | 1238 | Not measured | Only Claude Opus 4.8 measured |
| Design Arena: HTML slides | 1221 | Not measured | Only Claude Opus 4.8 measured |
| Design Arena: PowerPoint slides | 1227 | Not measured | Only Claude Opus 4.8 measured |
| LiveBench research | 81.8% | Not measured | Only Claude Opus 4.8 measured |
| LiveBench browser | 96.0% | Not measured | Only Claude Opus 4.8 measured |
| LiveBench long agentic | 48.3% | Not measured | Only Claude Opus 4.8 measured |
| Finance Agent (Vals AI) | 53.9% | Not measured | Only Claude Opus 4.8 measured |
| Tax Agent Bench (Vals AI) | 30.0% | Not measured | Only Claude Opus 4.8 measured |
| Legal Research Bench (Vals AI) | 43.8% | Not measured | Only Claude Opus 4.8 measured |
| Excel Modeling Benchmark (Vals AI) | 69.4% | Not measured | Only Claude Opus 4.8 measured |
| Terminal-Bench-Science (Vals AI) | 4.3% | Not measured | Only Claude Opus 4.8 measured |
| Time Horizon Index (Vals AI) | 11.8% | Not measured | Only Claude Opus 4.8 measured |
| τ²-Bench Telecom | 94.4% | 10.5% | Claude Opus 4.8 |
| APEX-Agents | 48.9% | Not measured | Only Claude Opus 4.8 measured |
| Remote Labor Index | 8.3% | Not measured | Only Claude Opus 4.8 measured |
| OSWorld 2.0 | 20.6% | Not measured | Only Claude Opus 4.8 measured |
| DeepResearch Bench | 50.2% | Not measured | Only Claude Opus 4.8 measured |
| PostTrainBench | 33.8% | Not measured | Only Claude Opus 4.8 measured |
| Vending-Bench 2 | $5,787 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Search | 1204 | Not measured | Only Claude Opus 4.8 measured |
| Neither model has a result on the other 13 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index80
| Benchmark | Claude Opus 4.8 | Gemma 3 27B | Leader |
|---|---|---|---|
| GPQA Diamond | 92.4% | Not measured | Only Claude Opus 4.8 measured |
| LiveBench reasoning | 89.2% | Not measured | Only Claude Opus 4.8 measured |
| MMMU Pro (Vals AI) | 86.6% | Not measured | Only Claude Opus 4.8 measured |
| GPQA Diamond (Artificial Analysis run) | 92.0% | 42.8% | Claude Opus 4.8 |
| Humanity's Last Exam (Artificial Analysis run) | 48.7% | 4.4% | Claude Opus 4.8 |
| GPQA Diamond (Epoch AI run) | 91.0% | 47.7% | Claude Opus 4.8 |
| ARC-AGI | 92.5% | Not measured | Only Claude Opus 4.8 measured |
| ARC-AGI-2 | 72.1% | Not measured | Only Claude Opus 4.8 measured |
| SimpleBench | 64.8% | Not measured | Only Claude Opus 4.8 measured |
| Chess puzzles | 52.0% | Not measured | Only Claude Opus 4.8 measured |
| Mystery game puzzles | 36.0% | Not measured | Only Claude Opus 4.8 measured |
| EBR-bench | 28.6% | Not measured | Only Claude Opus 4.8 measured |
| LMArena Text: hard prompts | 1482 | 1340 | Claude Opus 4.8 |
| LMArena Text: expert | 1503 | 1304 | Claude Opus 4.8 |
| LMArena Text: hard prompts in English | 1487 | 1353 | Claude Opus 4.8 |
| LMArena Vision: diagrams | 1315 | 1156 | Claude Opus 4.8 |
| LMArena Vision: homework | 1337 | 1160 | Claude Opus 4.8 |
| Neither model has a result on the other 4 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | Claude Opus 4.8 | Gemma 3 27B | Leader |
|---|---|---|---|
| AA Math Index | Not measured | 20.7 | Only Gemma 3 27B measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 20.7% | Only Gemma 3 27B measured |
| OTIS Mock AIME | 98.3% | 22.5% | Claude Opus 4.8 |
| FrontierMath, tiers 1 to 3 | 80.0% | Not measured | Only Claude Opus 4.8 measured |
| FrontierMath, tier 4 | 56.1% | Not measured | Only Claude Opus 4.8 measured |
| ProofBench | 69.0% | Not measured | Only Claude Opus 4.8 measured |
| MATH level 5 | Not measured | 74.0% | Only Gemma 3 27B measured |
| LMArena Text: math | 1486 | 1312 | Claude Opus 4.8 |
| LMArena Text: mathematical work | 1497 | 1327 | Claude Opus 4.8 |
| Neither model has a result on the other 4 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Claude Opus 4.8 | Gemma 3 27B | Leader |
|---|---|---|---|
| MMLU Pro | 89.6% | Not measured | Only Claude Opus 4.8 measured |
| LegalBench (Vals AI) | 83.6% | Not measured | Only Claude Opus 4.8 measured |
| CorpFin (Vals AI) | 66.7% | Not measured | Only Claude Opus 4.8 measured |
| TaxEval (Vals AI) | 75.6% | Not measured | Only Claude Opus 4.8 measured |
| MortgageTax (Vals AI) | 69.9% | Not measured | Only Claude Opus 4.8 measured |
| MedCode (Vals AI) | 53.2% | Not measured | Only Claude Opus 4.8 measured |
| MMLU Pro (Artificial Analysis run) | Not measured | 66.9% | Only Gemma 3 27B measured |
| SimpleQA Verified | 53.0% | Not measured | Only Claude Opus 4.8 measured |
| GeoBench | Not measured | 52.0% | Only Gemma 3 27B measured |
| LMArena Text: science | 1477 | 1383 | Claude Opus 4.8 |
| LMArena Text: medicine and healthcare | 1464 | 1391 | Claude Opus 4.8 |
| LMArena Text: legal and government | 1477 | 1375 | Claude Opus 4.8 |
| LMArena Text: business and finance | 1458 | 1360 | Claude Opus 4.8 |
| Neither model has a result on the other 4 boards here | |||
Web designDirectional onlyPublic boards, shown as published, kept out of the index9 boards, none shared
| Benchmark | Claude Opus 4.8 | Gemma 3 27B | Leader |
|---|---|---|---|
| Design Arena: websites | 1258 | Not measured | Only Claude Opus 4.8 measured |
| Design Arena: UI components | 1256 | Not measured | Only Claude Opus 4.8 measured |
| Design Arena: game dev | 1264 | Not measured | Only Claude Opus 4.8 measured |
| Design Arena: data viz | 1240 | Not measured | Only Claude Opus 4.8 measured |
| Design Arena: 3D | 1223 | Not measured | Only Claude Opus 4.8 measured |
| Design Arena: all code categories | 1255 | Not measured | Only Claude Opus 4.8 measured |
| Design Arena: SVG | 1194 | Not measured | Only Claude Opus 4.8 measured |
| Design Arena: ASCII art | 1276 | Not measured | Only Claude Opus 4.8 measured |
| LiveBench design | 78.8% | Not measured | Only Claude Opus 4.8 measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index270
| Benchmark | Claude Opus 4.8 | Gemma 3 27B | Leader |
|---|---|---|---|
| LiveBench data analysis | 66.0% | Not measured | Only Claude Opus 4.8 measured |
| Public Benefits Bench (Vals AI) | 68.1% | Not measured | Only Claude Opus 4.8 measured |
| SAGE (Vals AI) | 54.8% | Not measured | Only Claude Opus 4.8 measured |
| MedScribe (Vals AI) | 85.8% | Not measured | Only Claude Opus 4.8 measured |
| Vals Multimodal Index | 70.9% | Not measured | Only Claude Opus 4.8 measured |
| IFBench | 62.2% | 31.8% | Claude Opus 4.8 |
| Long context reasoning (AA-LCR) | 77.7% | 7.3% | Claude Opus 4.8 |
| DTBench | 94.9% | 52.5% | Claude Opus 4.8 |
| LMCA | 57.5% | 12.3% | Claude Opus 4.8 |
| Fiction.LiveBench | Not measured | 33.3% | Only Gemma 3 27B measured |
| Creative writing (Lech Mazur) | Not measured | 79.9% | Only Gemma 3 27B measured |
| Surface Evolver Bench | 87.5% | Not measured | Only Claude Opus 4.8 measured |
| Furniture assembly | 42.5% | Not measured | Only Claude Opus 4.8 measured |
| LMArena Text | 1461 | 1358 | Claude Opus 4.8 |
| LMArena Text: instruction following | 1476 | 1321 | Claude Opus 4.8 |
| LMArena Text: creative writing | 1454 | 1345 | Claude Opus 4.8 |
| LMArena Vision | 1294 | 1165 | Claude Opus 4.8 |
| LMArena Text: English | 1468 | 1377 | Claude Opus 4.8 |
| LMArena Text: non-English | 1450 | 1334 | Claude Opus 4.8 |
| LMArena Text: Chinese | 1506 | 1346 | Claude Opus 4.8 |
| LMArena Text: German | 1472 | 1362 | Claude Opus 4.8 |
| LMArena Text: Japanese | 1442 | 1287 | Claude Opus 4.8 |
| LMArena Text: Korean | 1431 | 1308 | Claude Opus 4.8 |
| LMArena Text: French | 1481 | 1368 | Claude Opus 4.8 |
| LMArena Text: Spanish | 1465 | 1349 | Claude Opus 4.8 |
| LMArena Text: Russian | 1474 | 1349 | Claude Opus 4.8 |
| LMArena Text: Polish | 1459 | 1345 | Claude Opus 4.8 |
| LMArena Text: multi-turn | 1476 | 1345 | Claude Opus 4.8 |
| LMArena Text: longer queries | 1483 | 1333 | Claude Opus 4.8 |
| LMArena Text: writing and language | 1461 | 1347 | Claude Opus 4.8 |
| LMArena Text: entertainment and media | 1440 | 1320 | Claude Opus 4.8 |
| LMArena Vision: English | 1293 | 1188 | Claude Opus 4.8 |
| LMArena Vision: Chinese | 1346 | 1164 | Claude Opus 4.8 |
| LMArena Vision: reading text | 1303 | 1156 | Claude Opus 4.8 |
| LMArena Vision: humor | 1282 | 1166 | Claude Opus 4.8 |
| LMArena Vision: captioning | Not measured | 1151 | Only Gemma 3 27B measured |
| LMArena Vision: recognizing things | Not measured | 1196 | Only Gemma 3 27B measured |
| LMArena Vision: creative writing | 1301 | 1177 | Claude Opus 4.8 |
| LMArena Document | 1475 | Not measured | Only Claude Opus 4.8 measured |
| Neither model has a result on the other 7 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Claude Opus 4.8 | Gemma 3 27B | 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
Claude Opus 4.8$0.018Fits in one request
Gemma 3 27B$0.0003Fits in one request
Gemma 3 27B costs less
Repository review
50K input + 3K output tokens
Claude Opus 4.8$0.325Fits in one request
Gemma 3 27B$0.0050Fits in one request
Gemma 3 27B costs less
Agent loop
200K input + 10K output tokens
Claude Opus 4.8$1.25Fits in one request
Gemma 3 27B$0.019Exceeds the context window
Gemma 3 27B 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 | Anthropic Claude Opus 4.8 | Google Gemma 3 27B |
|---|---|---|
| Maker | Anthropic | |
| Weights | No public weights listed | Open weights |
| Released | May 27, 2026 | March 12, 2025 |
| Context window | 1M | 131K |
| Input $/Mtok | $5.00 | $0.08 |
| Output $/Mtok | $25.00 | $0.35 |
| Coding index | 66.0 | 4.9 |
| Independent measurements behind it | 2 | 1 |
| Cost per solved task | $2.17 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Opus 4.8 better than Gemma 3 27B for coding?
Pick Claude Opus 4.8 for coding: it scores 66.0 on the Vibe Coding Index against 4.9 for Gemma 3 27B. Pick Gemma 3 27B when output tokens cost 71.4x less.
Which is cheaper, Claude Opus 4.8 or Gemma 3 27B?
Claude Opus 4.8 costs $5.00 per million input tokens and $25.00 per million output tokens; Gemma 3 27B costs $0.08 and $0.35. Cost per solved task is known for Claude Opus 4.8 only.
Which has the bigger context window, Claude Opus 4.8 or Gemma 3 27B?
Claude Opus 4.8, with 1M tokens against 131K.
How many benchmarks is the Claude Opus 4.8 vs Gemma 3 27B comparison based on?
51 benchmarks have a result for both models as of October 21, 2026. Claude Opus 4.8's coding index rests on 2 independent benchmarks and Gemma 3 27B's on 1. Where only one model has a result, the page says so instead of naming a winner.