Claude Sonnet 4.5 vs Gemini 3 Flash Preview
Updated October 21, 2026. 45 benchmarks have a result for both. Coding is ranked on the Vibe Coding Index; every other board is shown as published.
Decision reading
Pick Gemini 3 Flash Preview for coding: it scores 75.8 on the Vibe Coding Index against 59.1 for Claude Sonnet 4.5, though on 1 benchmark against 2.
Pick Claude Sonnet 4.5 when what matters is Vibe Code Bench (Vals AI) or GSO-Bench, where it leads.
- Shared results
- 45
- Claude Sonnet 4.5 only
- 47
- Gemini 3 Flash Preview only
- 24
- Like-for-like categories
- 8 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
Gemini 3 Flash Preview
Gemini 3 Flash Preview scores 75.8 against 59.1.
2 and 1 benchmarks behind the scores
Intelligence
AA Intelligence Index
Gemini 3 Flash Preview
Gemini 3 Flash Preview leads, 26.3 against 20.7.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Claude Sonnet 4.5 has a AA Agentic Index result, 15.8.
Directional only
Reasoning
GPQA Diamond
Gemini 3 Flash Preview
Gemini 3 Flash Preview leads, 87.9% against 81.6%.
Same board, both measured
Math
AIME
Gemini 3 Flash Preview
Gemini 3 Flash Preview leads, 95.6% against 88.2%.
Same board, both measured
Knowledge
MMLU Pro
Gemini 3 Flash Preview
Gemini 3 Flash Preview leads, 88.6% against 87.4%.
Same board, both measured
Web design
Design Arena: websites
Gemini 3 Flash Preview
Gemini 3 Flash Preview leads, 1196 against 1190.
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 Sonnet 4.5 $0.011, 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 Sonnet 4.5 $1.16, Gemini 3 Flash Preview $0.37.
Published attempt cost and pass rate
At a glance
- Coding index
- Claude Sonnet 4.5 59.1 from 2 benchmarks, Gemini 3 Flash Preview 75.8 from 1 benchmark.
- Widest category
- Reasoning, 15.6 points apart on average over 9 shared benchmarks.
- Widest single gap
- SimpleQA Verified: Claude Sonnet 4.5 30.7% against Gemini 3 Flash Preview 66.8%, 36.1 points apart on a 0 to 100 scale.
- Output price
- Claude Sonnet 4.5 $15.00 against Gemini 3 Flash Preview $3.00 per million output tokens, 5.0x apart.
- Context window
- Claude Sonnet 4.5 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 Sonnet 4.5 | Bars | Gemini 3 Flash Preview | Ties |
|---|---|---|---|---|
| Coding | 2 | 5 | ||
| Intelligence | 0 | 1 | ||
| Agentic work | 3 | 2 | ||
| Reasoning | 0 | 9 | ||
| Math | 2 | 4 | ||
| Knowledge | 1 | 8 | ||
| Web design | 0 | 3 | 1 tie | |
| General | 1 | 3 | ||
| All shared boards | 9 | 35 | 1 tie |
CodingLike-for-likeFour of these boards feed the Vibe Coding Index25
| Benchmark | Claude Sonnet 4.5 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| SWE-bench Verified | 74.8% | 75.8% | Gemini 3 Flash Preview |
| SWE-bench Multilingual | 67.0% | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena WebDev | 1394 | Not measured | Only Claude Sonnet 4.5 measured |
| AA Coding Index | 52.1 | Not measured | Only Claude Sonnet 4.5 measured |
| LiveCodeBench (Vals AI) | 73.0% | 85.6% | Gemini 3 Flash Preview |
| SWE-bench Verified (Vals AI) | 70.0% | 75.0% | Gemini 3 Flash Preview |
| Vibe Code Bench (Vals AI) | 22.6% | 20.2% | Claude Sonnet 4.5 |
| Code migration (Vals AI) | Not measured | 6.4% | Only Gemini 3 Flash Preview measured |
| ProgramBench (Vals AI) | Not measured | 0.0% | Only Gemini 3 Flash Preview measured |
| Terminal-Bench 2.1 (Vals AI) | Not measured | 53.9% | Only Gemini 3 Flash Preview measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 90.8% | Only Gemini 3 Flash Preview measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 38.6% | Only Gemini 3 Flash Preview measured |
| Terminal-Bench | 46.5% | 64.3% | Gemini 3 Flash Preview |
| GSO-Bench | 14.7% | 9.8% | Claude Sonnet 4.5 |
| WeirdML | 47.7% | 61.6% | Gemini 3 Flash Preview |
| Cybench | 60.0% | Not measured | Only Claude Sonnet 4.5 measured |
| ALE-Bench | Not measured | 1367.2 | Only Gemini 3 Flash Preview measured |
| LMArena Text: coding | 1488 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: software and IT | 1473 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena WebDev: React | 1386 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena WebDev: HTML | 1399 | Not measured | Only Claude Sonnet 4.5 measured |
| Neither model has a result on the other 17 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | Claude Sonnet 4.5 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| AA Intelligence Index | 20.7 | 26.3 | Gemini 3 Flash Preview |
| Epoch Capabilities Index | 146.7 | Not measured | Only Claude Sonnet 4.5 measured |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index32
| Benchmark | Claude Sonnet 4.5 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| AA Agentic Index | 15.8 | Not measured | Only Claude Sonnet 4.5 measured |
| Design Arena: agents building web apps | 1060 | 1111 | Gemini 3 Flash Preview |
| Design Arena: agents building full-stack apps | 1050 | 1063 | Gemini 3 Flash Preview |
| Design Arena: agents building mobile apps | 1137 | 1090 | Claude Sonnet 4.5 |
| Design Arena: agents building Android apps | Not measured | 1056 | Only Gemini 3 Flash Preview measured |
| Design Arena: agents building Godot games | Not measured | 1161 | Only Gemini 3 Flash Preview measured |
| Design Arena: PowerPoint slides | Not measured | 1036 | Only Gemini 3 Flash Preview measured |
| Finance Agent (Vals AI) | Not measured | 42.5% | Only Gemini 3 Flash Preview measured |
| Tax Agent Bench (Vals AI) | Not measured | 11.8% | Only Gemini 3 Flash Preview measured |
| Legal Research Bench (Vals AI) | Not measured | 18.3% | Only Gemini 3 Flash Preview measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 26.0% | Only Gemini 3 Flash Preview measured |
| τ²-Bench Telecom | Not measured | 80.4% | Only Gemini 3 Flash Preview measured |
| METR time horizons | 67.4% | Not measured | Only Claude Sonnet 4.5 measured |
| Remote Labor Index | 2.1% | Not measured | Only Claude Sonnet 4.5 measured |
| GDPval | 42.5% | Not measured | Only Claude Sonnet 4.5 measured |
| BALROG | Not measured | 48.1% | Only Gemini 3 Flash Preview measured |
| DeepResearch Bench | 52.6% | 49.8% | Claude Sonnet 4.5 |
| OSWorld | 62.9% | Not measured | Only Claude Sonnet 4.5 measured |
| Vending-Bench 2 | $3,839 | $3,635 | Claude Sonnet 4.5 |
| Neither model has a result on the other 20 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index09
| Benchmark | Claude Sonnet 4.5 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| GPQA Diamond | 81.6% | 87.9% | Gemini 3 Flash Preview |
| MMMU Pro (Vals AI) | 79.3% | 87.6% | Gemini 3 Flash Preview |
| GPQA Diamond (Artificial Analysis run) | Not measured | 89.8% | Only Gemini 3 Flash Preview measured |
| Humanity's Last Exam (Artificial Analysis run) | Not measured | 36.6% | Only Gemini 3 Flash Preview measured |
| GPQA Diamond (Epoch AI run) | 82.3% | 89.4% | Gemini 3 Flash Preview |
| ARC-AGI | 63.7% | 84.7% | Gemini 3 Flash Preview |
| ARC-AGI-2 | 13.6% | 33.6% | Gemini 3 Flash Preview |
| SimpleBench | 54.3% | 61.1% | Gemini 3 Flash Preview |
| Chess puzzles | 10.0% | 39.0% | Gemini 3 Flash Preview |
| Mystery game puzzles | 17.0% | 26.0% | Gemini 3 Flash Preview |
| EBR-bench | 2.4% | Not measured | Only Claude Sonnet 4.5 measured |
| VPCT | 39.8% | 72.6% | Gemini 3 Flash Preview |
| LMArena Text: hard prompts | 1462 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: expert | 1483 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: hard prompts in English | 1471 | Not measured | Only Claude Sonnet 4.5 measured |
| Neither model has a result on the other 6 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index24
| Benchmark | Claude Sonnet 4.5 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| AIME | 88.2% | 95.6% | Gemini 3 Flash Preview |
| MGSM (Vals AI) | 94.3% | 93.3% | Claude Sonnet 4.5 |
| 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 | 77.8% | 95.6% | Gemini 3 Flash Preview |
| FrontierMath, tiers 1 to 3 | 23.9% | 51.2% | Gemini 3 Flash Preview |
| FrontierMath, tier 4 | 2.4% | 17.1% | Gemini 3 Flash Preview |
| ProofBench | 19.0% | 15.0% | Claude Sonnet 4.5 |
| MATH level 5 | 97.7% | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: math | 1449 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: mathematical work | 1462 | Not measured | Only Claude Sonnet 4.5 measured |
| Neither model has a result on the other 2 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index18
| Benchmark | Claude Sonnet 4.5 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| MMLU Pro | 87.4% | 88.6% | Gemini 3 Flash Preview |
| LegalBench (Vals AI) | 84.1% | 86.9% | Gemini 3 Flash Preview |
| CaseLaw (Vals AI) | 62.2% | 55.8% | Claude Sonnet 4.5 |
| CorpFin (Vals AI) | 62.0% | 66.4% | Gemini 3 Flash Preview |
| TaxEval (Vals AI) | 73.3% | 73.9% | Gemini 3 Flash Preview |
| MortgageTax (Vals AI) | 64.0% | 68.7% | Gemini 3 Flash Preview |
| MedQA (Vals AI) | 94.7% | 95.8% | Gemini 3 Flash Preview |
| MedCode (Vals AI) | 44.1% | 55.9% | Gemini 3 Flash Preview |
| MMLU Pro (Artificial Analysis run) | Not measured | 89.0% | Only Gemini 3 Flash Preview measured |
| SimpleQA Verified | 30.7% | 66.8% | Gemini 3 Flash Preview |
| GeoBench | Not measured | 88.0% | Only Gemini 3 Flash Preview measured |
| LMArena Text: science | 1448 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: medicine and healthcare | 1444 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: legal and government | 1451 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: business and finance | 1440 | Not measured | Only Claude Sonnet 4.5 measured |
| Neither model has a result on the other 2 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index03
| Benchmark | Claude Sonnet 4.5 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| Design Arena: websites | 1190 | 1196 | Gemini 3 Flash Preview |
| Design Arena: UI components | 1173 | Not measured | Only Claude Sonnet 4.5 measured |
| Design Arena: game dev | 1166 | 1166 | Tie |
| Design Arena: data viz | 1167 | Not measured | Only Claude Sonnet 4.5 measured |
| Design Arena: 3D | 1158 | 1184 | Gemini 3 Flash Preview |
| Design Arena: all code categories | 1183 | 1189 | Gemini 3 Flash Preview |
| Design Arena: SVG | 1114 | Not measured | Only Claude Sonnet 4.5 measured |
| Design Arena: ASCII art | 1204 | Not measured | Only Claude Sonnet 4.5 measured |
| Neither model has a result on the other 1 board here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index13
| Benchmark | Claude Sonnet 4.5 | Gemini 3 Flash Preview | Leader |
|---|---|---|---|
| SAGE (Vals AI) | 36.1% | 51.8% | Gemini 3 Flash Preview |
| MedScribe (Vals AI) | 84.5% | 69.9% | Claude Sonnet 4.5 |
| Vals Multimodal Index | Not measured | 52.2% | Only Gemini 3 Flash Preview measured |
| IFBench | Not measured | 78.0% | Only Gemini 3 Flash Preview measured |
| Long context reasoning (AA-LCR) | Not measured | 78.0% | Only Gemini 3 Flash Preview measured |
| DTBench | 83.2% | 89.1% | Gemini 3 Flash Preview |
| LMCA | 38.8% | 43.1% | Gemini 3 Flash Preview |
| LMArena Text | 1438 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: instruction following | 1459 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: creative writing | 1442 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: English | 1450 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: non-English | 1425 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: Chinese | 1460 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: German | 1427 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: Japanese | 1390 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: Korean | 1402 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: French | 1459 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: Spanish | 1458 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: Russian | 1437 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: Polish | 1423 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: multi-turn | 1465 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: longer queries | 1475 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: writing and language | 1442 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Text: entertainment and media | 1428 | Not measured | Only Claude Sonnet 4.5 measured |
| LMArena Document | 1450 | Not measured | Only Claude Sonnet 4.5 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 | Claude Sonnet 4.5 | 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 Sonnet 4.5 | Google Gemini 3 Flash Preview |
|---|---|---|
| Maker | Anthropic | |
| Weights | No public weights listed | No public weights listed |
| Released | September 29, 2025 | December 17, 2025 |
| Context window | 1M | 1.05M |
| Input $/Mtok | $3.00 | $0.50 |
| Output $/Mtok | $15.00 | $3.00 |
| Coding index | 59.1 | 75.8 |
| Independent measurements behind it | 2 | 1 |
| Cost per solved task | $1.16 | $0.37 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Claude Sonnet 4.5 better than Gemini 3 Flash Preview for coding?
Pick Gemini 3 Flash Preview for coding: it scores 75.8 on the Vibe Coding Index against 59.1 for Claude Sonnet 4.5, though on 1 benchmark against 2. Pick Claude Sonnet 4.5 when what matters is Vibe Code Bench (Vals AI) or GSO-Bench, where it leads.
Which is cheaper, Claude Sonnet 4.5 or Gemini 3 Flash Preview?
Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens; Gemini 3 Flash Preview costs $0.50 and $3.00. Per solved SWE-bench Verified task, Claude Sonnet 4.5 costs $1.16 and Gemini 3 Flash Preview $0.37.
Which has the bigger context window, Claude Sonnet 4.5 or Gemini 3 Flash Preview?
Gemini 3 Flash Preview, with 1.05M tokens against 1M.
How many benchmarks is the Claude Sonnet 4.5 vs Gemini 3 Flash Preview comparison based on?
45 benchmarks have a result for both models as of October 21, 2026. Claude Sonnet 4.5's coding index rests on 2 independent benchmarks and Gemini 3 Flash Preview's on 1. Where only one model has a result, the page says so instead of naming a winner.