Claude Opus 4.8 vs Gemini 3 Flash Preview
Claude Opus 4.8 leads Gemini 3 Flash Preview on coding, 65.0 to 43.7 on the Vibe Coding Index, and Gemini 3 Flash Preview costs 8.3x less per output token ($3.00 vs $25.00 per million). Updated October 22, 2026; 57 benchmarks have a result for both.
Claude Opus 4.8 or Gemini 3 Flash Preview: which to pick
Pick Claude Opus 4.8 for coding: it scores 65.0 on the Vibe Coding Index against 43.7 for Gemini 3 Flash Preview.
Pick Gemini 3 Flash Preview for output tokens 8.3x cheaper ($3.00 vs $25.00 per million) and a lower cost per solved task ($0.37 against $2.17).
- Shared results
- 57
- Claude Opus 4.8 only
- 73
- Gemini 3 Flash Preview only
- 14
- Like-for-like categories
- 8 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
Claude Opus 4.8
Claude Opus 4.8 scores 65.0 against 43.7.
6 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
Claude Opus 4.8
Claude Opus 4.8 leads, 41.8 against 26.3.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Claude Opus 4.8 has a AA Agentic Index result, 41.9.
Directional only
Reasoning
GPQA Diamond
Claude Opus 4.8
Claude Opus 4.8 leads, 92.4% against 87.9%.
Same board, both measured
Math
AIME
No call
Only Gemini 3 Flash Preview has a AIME result, 95.6%.
Directional only
Knowledge
MMLU Pro
Claude Opus 4.8
Claude Opus 4.8 leads, 89.6% against 88.6%.
Same board, both measured
Web design
Design Arena: websites
Claude Opus 4.8
Claude Opus 4.8 leads, 1258 against 1196.
Same board, both measured
Long documents
Listed context window
Gemini 3 Flash Preview
Gemini 3 Flash Preview takes 1.05M tokens against 1M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Gemini 3 Flash Preview
Claude Opus 4.8 $0.018, Gemini 3 Flash Preview $0.0020 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Gemini 3 Flash Preview
Claude Opus 4.8 $2.17, Gemini 3 Flash Preview $0.37.
Published attempt cost and pass rate
At a glance
- Coding index
- Claude Opus 4.8 65.0 from 6 benchmarks, Gemini 3 Flash Preview 43.7 from 2 benchmarks.
- Widest category
- Math, 31.1 points apart on average over 4 shared benchmarks.
- Widest single gap
- Vibe Code Bench (Vals AI): Claude Opus 4.8 82.7% against Gemini 3 Flash Preview 20.2%, 62.5 points apart on a 0 to 100 scale.
- Output price
- Claude Opus 4.8 $25.00 against Gemini 3 Flash Preview $3.00 per million output tokens, 8.3x apart.
- Context window
- Claude Opus 4.8 takes 1M tokens, Gemini 3 Flash Preview 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 | Claude Opus 4.8 | Bars | Gemini 3 Flash Preview | Ties |
|---|---|---|---|---|
| Coding | 9 | 1 | ||
| Intelligence | 1 | 0 | ||
| Agentic work | 13 | 0 | ||
| Reasoning | 9 | 1 | ||
| Math | 4 | 0 | ||
| Knowledge | 4 | 4 | ||
| Web design | 4 | 0 | ||
| General | 5 | 2 | ||
| All shared boards | 49 | 8 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index91
| Benchmark | Claude Opus 4.8 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| SWE-bench Verified | Not measured | 75.8% | Only Gemini 3 Flash Preview 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 | Not measured | Only Claude Opus 4.8 measured |
| LiveCodeBench (Vals AI) | 87.8% | 85.6% | Claude Opus 4.8 |
| SWE-bench Verified (Vals AI) | 88.6% | 75.0% | Claude Opus 4.8 |
| Terminal-Bench 4 (Vals AI) | 23.2% | Not measured | Only Claude Opus 4.8 measured |
| Vibe Code Bench (Vals AI) | 82.7% | 20.2% | Claude Opus 4.8 |
| Code migration (Vals AI) | 47.3% | 6.4% | Claude Opus 4.8 |
| ProgramBench (Vals AI) | 1.0% | 0.0% | Claude Opus 4.8 |
| Terminal-Bench 2.1 (Vals AI) | 71.9% | 53.9% | Claude Opus 4.8 |
| SkillsBench (Vals AI) | 59.2% | Not measured | Only Claude Opus 4.8 measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 90.8% | Only Gemini 3 Flash Preview measured |
| SciCode | 54.4% | Not measured | Only Claude Opus 4.8 measured |
| Terminal-Bench Hard (Artificial Analysis run) | 58.3% | 38.6% | Claude Opus 4.8 |
| Terminal-Bench | Not measured | 64.3% | Only Gemini 3 Flash Preview measured |
| FrontierCode | 46.5% | Not measured | Only Claude Opus 4.8 measured |
| GSO-Bench | 47.1% | 9.8% | Claude Opus 4.8 |
| WeirdML | 82.9% | 61.6% | Claude Opus 4.8 |
| ALE-Bench | Not measured | 1367.2 | Only Gemini 3 Flash Preview measured |
| LMArena Text: coding | 1490 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Text: software and IT | 1488 | Not measured | Only Claude Opus 4.8 measured |
| LMArena WebDev: React | 1557 | Not measured | Only Claude Opus 4.8 measured |
| LMArena WebDev: HTML | 1543 | Not measured | Only Claude Opus 4.8 measured |
| SciCode | 12.3% | 12.7% | Gemini 3 Flash Preview |
| Neither model has a result on the other 14 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index10
| Benchmark | Claude Opus 4.8 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| AA Intelligence Index | 41.8 | 26.3 | Claude Opus 4.8 |
| Epoch Capabilities Index | 159.0 | Not measured | Only Claude Opus 4.8 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index130
| Benchmark | Claude Opus 4.8 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| AA Agentic Index | 41.9 | Not measured | Only Claude Opus 4.8 measured |
| Design Arena: agents building web apps | 1233 | 1111 | Claude Opus 4.8 |
| Design Arena: agents building full-stack apps | 1249 | 1063 | Claude Opus 4.8 |
| Design Arena: agents building mobile apps | 1222 | 1090 | Claude Opus 4.8 |
| Design Arena: agents building Android apps | 1233 | 1051 | Claude Opus 4.8 |
| Design Arena: agents building Godot games | 1231 | 1161 | Claude Opus 4.8 |
| Design Arena: agents building games | 1239 | Not measured | Only Claude Opus 4.8 measured |
| Design Arena: HTML slides | 1171 | Not measured | Only Claude Opus 4.8 measured |
| Design Arena: PowerPoint slides | 1202 | 1036 | Claude Opus 4.8 |
| Design Arena: spreadsheets | 1303 | 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% | 42.5% | Claude Opus 4.8 |
| Tax Agent Bench (Vals AI) | 30.0% | 11.8% | Claude Opus 4.8 |
| Legal Research Bench (Vals AI) | 43.8% | 18.3% | Claude Opus 4.8 |
| Excel Modeling Benchmark (Vals AI) | 69.4% | 26.0% | Claude Opus 4.8 |
| 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% | 80.4% | 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 |
| BALROG | Not measured | 48.1% | Only Gemini 3 Flash Preview measured |
| DeepResearch Bench | 50.2% | 49.8% | Claude Opus 4.8 |
| PostTrainBench | 33.8% | Not measured | Only Claude Opus 4.8 measured |
| Vending-Bench 2 | $5,787 | $3,635 | Claude Opus 4.8 |
| 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 index91
| Benchmark | Claude Opus 4.8 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| GPQA Diamond | 92.4% | 87.9% | Claude Opus 4.8 |
| LiveBench reasoning | 89.2% | Not measured | Only Claude Opus 4.8 measured |
| MMMU Pro (Vals AI) | 86.6% | 87.6% | Gemini 3 Flash Preview |
| GPQA Diamond (Artificial Analysis run) | 92.0% | 89.8% | Claude Opus 4.8 |
| Humanity's Last Exam (Artificial Analysis run) | 48.7% | 36.6% | Claude Opus 4.8 |
| GPQA Diamond (Epoch AI run) | 91.0% | 89.4% | Claude Opus 4.8 |
| ARC-AGI | 92.5% | 84.7% | Claude Opus 4.8 |
| ARC-AGI-2 | 72.1% | 33.6% | Claude Opus 4.8 |
| SimpleBench | 64.8% | 61.1% | Claude Opus 4.8 |
| Chess puzzles | 52.0% | 39.0% | Claude Opus 4.8 |
| Mystery game puzzles | 36.0% | 26.0% | Claude Opus 4.8 |
| EBR-bench | 28.6% | Not measured | Only Claude Opus 4.8 measured |
| VPCT | Not measured | 72.6% | Only Gemini 3 Flash Preview measured |
| LMArena Text: hard prompts | 1482 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Text: expert | 1503 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Text: hard prompts in English | 1487 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Vision: diagrams | 1315 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Vision: homework | 1337 | Not measured | Only Claude Opus 4.8 measured |
| Kagi LLM Benchmark | 88.8% | Not measured | Only Claude Opus 4.8 measured |
| Neither model has a result on the other 3 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Claude Opus 4.8 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| AIME | Not measured | 95.6% | Only Gemini 3 Flash Preview measured |
| MGSM (Vals AI) | Not measured | 93.3% | Only Gemini 3 Flash Preview measured |
| AA Math Index | Not measured | 97.0 | Only Gemini 3 Flash Preview measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 97.0% | Only Gemini 3 Flash Preview measured |
| OTIS Mock AIME | 98.3% | 95.6% | Claude Opus 4.8 |
| FrontierMath, tiers 1 to 3 | 80.0% | 51.2% | Claude Opus 4.8 |
| FrontierMath, tier 4 | 56.1% | 17.1% | Claude Opus 4.8 |
| ProofBench | 69.0% | 15.0% | Claude Opus 4.8 |
| LMArena Text: math | 1486 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Text: mathematical work | 1497 | Not measured | Only Claude Opus 4.8 measured |
| Neither model has a result on the other 3 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index44
| Benchmark | Claude Opus 4.8 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| MMLU Pro | 89.6% | 88.6% | Claude Opus 4.8 |
| LegalBench (Vals AI) | 83.6% | 86.9% | Gemini 3 Flash Preview |
| CaseLaw (Vals AI) | Not measured | 55.8% | Only Gemini 3 Flash Preview measured |
| CorpFin (Vals AI) | 66.7% | 66.4% | Claude Opus 4.8 |
| TaxEval (Vals AI) | 75.6% | 73.9% | Claude Opus 4.8 |
| MortgageTax (Vals AI) | 69.9% | 68.7% | Claude Opus 4.8 |
| MedQA (Vals AI) | Not measured | 95.8% | Only Gemini 3 Flash Preview measured |
| MedCode (Vals AI) | 53.2% | 55.9% | Gemini 3 Flash Preview |
| MMLU Pro (Artificial Analysis run) | Not measured | 89.0% | Only Gemini 3 Flash Preview measured |
| SimpleQA Verified | 53.0% | 66.8% | Gemini 3 Flash Preview |
| GeoBench | Not measured | 88.0% | Only Gemini 3 Flash Preview measured |
| LMArena Text: science | 1477 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Text: medicine and healthcare | 1464 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Text: legal and government | 1477 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Text: business and finance | 1458 | Not measured | Only Claude Opus 4.8 measured |
| FACTS Benchmark Suite | 53.5% | 63.4% | Gemini 3 Flash Preview |
| Neither model has a result on the other 2 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index40
| Benchmark | Claude Opus 4.8 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| Design Arena: websites | 1258 | 1196 | Claude Opus 4.8 |
| Design Arena: UI components | 1255 | Not measured | Only Claude Opus 4.8 measured |
| Design Arena: game dev | 1264 | 1166 | Claude Opus 4.8 |
| Design Arena: data viz | 1240 | Not measured | Only Claude Opus 4.8 measured |
| Design Arena: 3D | 1222 | 1183 | Claude Opus 4.8 |
| Design Arena: all code categories | 1255 | 1189 | Claude Opus 4.8 |
| Design Arena: SVG | 1195 | Not measured | Only Claude Opus 4.8 measured |
| Design Arena: ASCII art | 1277 | 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 index52
| Benchmark | Claude Opus 4.8 | Gemini 3 Flash Preview | 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% | 51.8% | Claude Opus 4.8 |
| MedScribe (Vals AI) | 85.8% | 69.9% | Claude Opus 4.8 |
| Vals Multimodal Index | 70.9% | 52.2% | Claude Opus 4.8 |
| IFBench | 62.2% | 78.0% | Gemini 3 Flash Preview |
| Long context reasoning (AA-LCR) | 77.7% | 78.0% | Gemini 3 Flash Preview |
| DTBench | 94.9% | 89.1% | Claude Opus 4.8 |
| LMCA | 57.5% | 43.1% | Claude Opus 4.8 |
| 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 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Text: instruction following | 1476 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Text: creative writing | 1454 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Vision | 1294 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Text: English | 1468 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Text: non-English | 1450 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Text: Chinese | 1506 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Text: German | 1472 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Text: Japanese | 1442 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Text: Korean | 1431 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Text: French | 1481 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Text: Spanish | 1465 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Text: Russian | 1474 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Text: Polish | 1459 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Text: multi-turn | 1476 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Text: longer queries | 1483 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Text: writing and language | 1461 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Text: entertainment and media | 1440 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Vision: English | 1293 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Vision: Chinese | 1346 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Vision: reading text | 1303 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Vision: humor | 1282 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Vision: creative writing | 1301 | Not measured | Only Claude Opus 4.8 measured |
| LMArena Document | 1475 | Not measured | Only Claude Opus 4.8 measured |
| 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 | Claude Opus 4.8 | Gemini 3 Flash Preview | 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 3 Flash Preview costs less
Repository review
50K input + 3K output tokens
Gemini 3 Flash Preview costs less
Agent loop
200K input + 10K output tokens
Gemini 3 Flash Preview 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 Gemini 3 Flash Preview |
|---|---|---|
| Maker | Anthropic | |
| Weights | No public weights listed | No public weights listed |
| Released | May 27, 2026 | December 17, 2025 |
| Context window | 1M | 1.05M |
| Input $/Mtok | $5.00 | $0.50 |
| Output $/Mtok | $25.00 | $3.00 |
| Coding index | 65.0 | 43.7 |
| Independent measurements behind it | 6 | 2 |
| Cost per solved task | $2.17 | $0.37 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Opus 4.8 better than Gemini 3 Flash Preview for coding?
Pick Claude Opus 4.8 for coding: it scores 65.0 on the Vibe Coding Index against 43.7 for Gemini 3 Flash Preview. Pick Gemini 3 Flash Preview for output tokens 8.3x cheaper ($3.00 vs $25.00 per million) and a lower cost per solved task ($0.37 against $2.17).
Which is cheaper, Claude Opus 4.8 or Gemini 3 Flash Preview?
Claude Opus 4.8 costs $5.00 per million input tokens and $25.00 per million output tokens; Gemini 3 Flash Preview costs $0.50 and $3.00. Per solved SWE-bench Verified task, Claude Opus 4.8 costs $2.17 and Gemini 3 Flash Preview $0.37.
Which has the bigger context window, Claude Opus 4.8 or Gemini 3 Flash Preview?
Gemini 3 Flash Preview, with 1.05M tokens against 1M.
How many benchmarks is the Claude Opus 4.8 vs Gemini 3 Flash Preview comparison based on?
57 benchmarks have a result for both models as of October 22, 2026. Claude Opus 4.8's coding index rests on 6 independent benchmarks and Gemini 3 Flash Preview's on 2. Where only one model has a result, the page says so instead of naming a winner.