Gemini 3.7 Flash vs Grok 4.20
Gemini 3.7 Flash leads Grok 4.20 on coding, 58.0 to 33.3 on the Vibe Coding Index, and Grok 4.20 costs 1.5x less per output token ($2.50 vs $3.75 per million). Updated October 21, 2026; 40 benchmarks have a result for both.
Gemini 3.7 Flash or Grok 4.20: which to pick
Pick Gemini 3.7 Flash for coding: it scores 58.0 on the Vibe Coding Index against 33.3 for Grok 4.20.
Pick Grok 4.20 for output tokens 1.5x cheaper ($2.50 vs $3.75 per million) and a lower cost per solved task ($0.72 against $1.78).
- Shared results
- 40
- Gemini 3.7 Flash only
- 72
- Grok 4.20 only
- 14
- Like-for-like categories
- 7 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
Gemini 3.7 Flash
Gemini 3.7 Flash scores 58.0 against 33.3.
6 and 2 benchmarks behind the scores
Intelligence
AA Intelligence Index
Gemini 3.7 Flash
Gemini 3.7 Flash leads, 39.6 against 25.7.
Same board, both measured
Reasoning
GPQA Diamond
Gemini 3.7 Flash
Gemini 3.7 Flash leads, 93.9% against 88.6%.
Same board, both measured
Math
AIME
No call
Only Grok 4.20 has a AIME result, 96.5%.
Directional only
Knowledge
MMLU Pro
Gemini 3.7 Flash
Gemini 3.7 Flash leads, 90.1% against 86.3%.
Same board, both measured
Web design
Design Arena: websites
Gemini 3.7 Flash
Gemini 3.7 Flash leads, 1304 against 1229.
Same board, both measured
Long documents
Listed context window
Grok 4.20
Grok 4.20 takes 2M tokens against 1.05M.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Grok 4.20
Gemini 3.7 Flash $0.0026, Grok 4.20 $0.0025 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
Grok 4.20
Gemini 3.7 Flash $1.78, Grok 4.20 $0.72.
Published attempt cost and pass rate
At a glance
- Coding index
- Gemini 3.7 Flash 58.0 from 6 benchmarks, Grok 4.20 33.3 from 2 benchmarks.
- Widest category
- Coding, 29.4 points apart on average over 5 shared benchmarks.
- Widest single gap
- Vibe Code Bench (Vals AI): Gemini 3.7 Flash 70.4% against Grok 4.20 4.1%, 66.3 points apart on a 0 to 100 scale.
- Output price
- Gemini 3.7 Flash $3.75 against Grok 4.20 $2.50 per million output tokens, 1.5x apart.
- Context window
- Gemini 3.7 Flash takes 1.05M tokens, Grok 4.20 2M.
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 | Gemini 3.7 Flash | Bars | Grok 4.20 | Ties |
|---|---|---|---|---|
| Coding | 5 | 0 | ||
| Intelligence | 2 | 0 | ||
| Agentic work | 9 | 0 | ||
| Reasoning | 6 | 0 | ||
| Knowledge | 5 | 0 | ||
| Web design | 8 | 0 | ||
| General | 5 | 0 | ||
| All shared boards | 40 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index50
| Benchmark | Gemini 3.7 Flash | Grok 4.20 | Leader |
|---|---|---|---|
| LiveBench coding | 80.5% | Not measured | Only Gemini 3.7 Flash measured |
| LMArena WebDev | 1591 | Not measured | Only Gemini 3.7 Flash measured |
| AA Coding Index | 71.5 | Not measured | Only Gemini 3.7 Flash measured |
| LiveCodeBench (Vals AI) | 88.7% | 84.3% | Gemini 3.7 Flash |
| SWE-bench Verified (Vals AI) | 80.8% | 72.2% | Gemini 3.7 Flash |
| Terminal-Bench 4 (Vals AI) | 12.1% | Not measured | Only Gemini 3.7 Flash measured |
| Vibe Code Bench (Vals AI) | 70.4% | 4.1% | Gemini 3.7 Flash |
| Code migration (Vals AI) | 34.8% | 0.3% | Gemini 3.7 Flash |
| ProgramBench (Vals AI) | 0.0% | Not measured | Only Gemini 3.7 Flash measured |
| IOI (Vals AI) | 67.8% | Not measured | Only Gemini 3.7 Flash measured |
| Terminal-Bench 2.1 (Vals AI) | 77.5% | 44.2% | Gemini 3.7 Flash |
| SkillsBench (Vals AI) | 65.9% | Not measured | Only Gemini 3.7 Flash measured |
| CyberBench (Vals AI) | 43.8% | Not measured | Only Gemini 3.7 Flash measured |
| SciCode | 59.8% | Not measured | Only Gemini 3.7 Flash measured |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 37.9% | Only Grok 4.20 measured |
| Terminal-Bench | Not measured | 57.3% | Only Grok 4.20 measured |
| FrontierCode | 43.6% | Not measured | Only Gemini 3.7 Flash measured |
| FrontierSWE | 20.3% | Not measured | Only Gemini 3.7 Flash measured |
| WeirdML | Not measured | 52.3% | Only Grok 4.20 measured |
| ALE-Bench | 904.3 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Text: coding | 1499 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Text: software and IT | 1498 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena WebDev: React | 1587 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena WebDev: HTML | 1593 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena WebDev: from an image | 1599 | Not measured | Only Gemini 3.7 Flash measured |
| Neither model has a result on the other 13 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Gemini 3.7 Flash | Grok 4.20 | Leader |
|---|---|---|---|
| AA Intelligence Index | 39.6 | 25.7 | Gemini 3.7 Flash |
| Epoch Capabilities Index | 158.0 | 152.1 | Gemini 3.7 Flash |
Agentic workLike-for-likePublic boards, shown as published, kept out of the index90
| Benchmark | Gemini 3.7 Flash | Grok 4.20 | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | 1223 | 1144 | Gemini 3.7 Flash |
| Design Arena: agents building full-stack apps | 1208 | 1054 | Gemini 3.7 Flash |
| Design Arena: agents building mobile apps | 1230 | 1090 | Gemini 3.7 Flash |
| Design Arena: agents building Android apps | 1242 | 1052 | Gemini 3.7 Flash |
| Design Arena: agents building Godot games | 1264 | 1089 | Gemini 3.7 Flash |
| Design Arena: agents building games | 1235 | Not measured | Only Gemini 3.7 Flash measured |
| Design Arena: HTML slides | Not measured | 1180 | Only Grok 4.20 measured |
| Design Arena: spreadsheets | 1053 | Not measured | Only Gemini 3.7 Flash measured |
| LiveBench research | 76.5% | Not measured | Only Gemini 3.7 Flash measured |
| LiveBench browser | 56.0% | Not measured | Only Gemini 3.7 Flash measured |
| LiveBench long agentic | 28.3% | Not measured | Only Gemini 3.7 Flash measured |
| SREBench (Vals AI) | 4.6% | Not measured | Only Gemini 3.7 Flash measured |
| Finance Agent (Vals AI) | 59.0% | 28.5% | Gemini 3.7 Flash |
| Tax Agent Bench (Vals AI) | 22.8% | 7.0% | Gemini 3.7 Flash |
| Legal Research Bench (Vals AI) | 34.6% | 13.9% | Gemini 3.7 Flash |
| Excel Modeling Benchmark (Vals AI) | 71.3% | 11.7% | Gemini 3.7 Flash |
| Terminal-Bench-Science (Vals AI) | 7.1% | Not measured | Only Gemini 3.7 Flash measured |
| τ²-Bench Telecom | Not measured | 93.0% | Only Grok 4.20 measured |
| APEX-Agents | 67.8% | Not measured | Only Gemini 3.7 Flash measured |
| Remote Labor Index | 5.0% | Not measured | Only Gemini 3.7 Flash measured |
| Vending-Bench 2 | Not measured | $4,663 | Only Grok 4.20 measured |
| Neither model has a result on the other 18 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index60
| Benchmark | Gemini 3.7 Flash | Grok 4.20 | Leader |
|---|---|---|---|
| GPQA Diamond | 93.9% | 88.6% | Gemini 3.7 Flash |
| LiveBench reasoning | 87.8% | Not measured | Only Gemini 3.7 Flash measured |
| MMMU Pro (Vals AI) | 89.0% | 83.5% | Gemini 3.7 Flash |
| GPQA Diamond (Artificial Analysis run) | 94.5% | 91.1% | Gemini 3.7 Flash |
| Humanity's Last Exam (Artificial Analysis run) | 47.9% | 34.5% | Gemini 3.7 Flash |
| GPQA Diamond (Epoch AI run) | 94.8% | Not measured | Only Gemini 3.7 Flash measured |
| ARC-AGI | 95.5% | 89.5% | Gemini 3.7 Flash |
| ARC-AGI-2 | 84.6% | 65.1% | Gemini 3.7 Flash |
| Chess puzzles | 66.0% | Not measured | Only Gemini 3.7 Flash measured |
| Mystery game puzzles | 37.0% | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Text: hard prompts | 1495 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Text: expert | 1512 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Text: hard prompts in English | 1487 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Vision: diagrams | 1329 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Vision: homework | 1320 | Not measured | Only Gemini 3.7 Flash measured |
| Neither model has a result on the other 6 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index7 boards, none shared
| Benchmark | Gemini 3.7 Flash | Grok 4.20 | Leader |
|---|---|---|---|
| AIME | Not measured | 96.5% | Only Grok 4.20 measured |
| OTIS Mock AIME | 97.2% | Not measured | Only Gemini 3.7 Flash measured |
| FrontierMath, tiers 1 to 3 | 71.6% | Not measured | Only Gemini 3.7 Flash measured |
| FrontierMath, tier 4 | 36.6% | Not measured | Only Gemini 3.7 Flash measured |
| ProofBench | 58.0% | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Text: math | 1511 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Text: mathematical work | 1502 | Not measured | Only Gemini 3.7 Flash measured |
| Neither model has a result on the other 6 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Gemini 3.7 Flash | Grok 4.20 | Leader |
|---|---|---|---|
| MMLU Pro | 90.1% | 86.3% | Gemini 3.7 Flash |
| LegalBench (Vals AI) | 87.3% | 77.7% | Gemini 3.7 Flash |
| CaseLaw (Vals AI) | Not measured | 54.4% | Only Grok 4.20 measured |
| CorpFin (Vals AI) | Not measured | 63.7% | Only Grok 4.20 measured |
| TaxEval (Vals AI) | 74.7% | 74.1% | Gemini 3.7 Flash |
| MortgageTax (Vals AI) | 66.7% | 45.4% | Gemini 3.7 Flash |
| MedQA (Vals AI) | Not measured | 94.5% | Only Grok 4.20 measured |
| MedCode (Vals AI) | 53.4% | 32.2% | Gemini 3.7 Flash |
| SimpleQA Verified | 69.2% | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Text: science | 1511 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Text: medicine and healthcare | 1494 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Text: legal and government | 1496 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Text: business and finance | 1479 | Not measured | Only Gemini 3.7 Flash measured |
| Neither model has a result on the other 4 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index80
| Benchmark | Gemini 3.7 Flash | Grok 4.20 | Leader |
|---|---|---|---|
| Design Arena: websites | 1304 | 1229 | Gemini 3.7 Flash |
| Design Arena: UI components | 1299 | 1199 | Gemini 3.7 Flash |
| Design Arena: game dev | 1318 | 1192 | Gemini 3.7 Flash |
| Design Arena: data viz | 1315 | 1217 | Gemini 3.7 Flash |
| Design Arena: 3D | 1308 | 1193 | Gemini 3.7 Flash |
| Design Arena: all code categories | 1308 | 1221 | Gemini 3.7 Flash |
| Design Arena: SVG | 1283 | 1164 | Gemini 3.7 Flash |
| Design Arena: ASCII art | 1276 | 1174 | Gemini 3.7 Flash |
| LiveBench design | 73.2% | Not measured | Only Gemini 3.7 Flash measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index50
| Benchmark | Gemini 3.7 Flash | Grok 4.20 | Leader |
|---|---|---|---|
| LiveBench data analysis | 68.0% | Not measured | Only Gemini 3.7 Flash measured |
| SAGE (Vals AI) | 49.2% | 38.2% | Gemini 3.7 Flash |
| MedScribe (Vals AI) | 83.9% | 63.4% | Gemini 3.7 Flash |
| Vals Multimodal Index | Not measured | 39.1% | Only Grok 4.20 measured |
| IFBench | Not measured | 81.2% | Only Grok 4.20 measured |
| Long context reasoning (AA-LCR) | 83.0% | 69.0% | Gemini 3.7 Flash |
| DTBench | 96.8% | 90.1% | Gemini 3.7 Flash |
| LMCA | 50.4% | 38.7% | Gemini 3.7 Flash |
| CL-bench | Not measured | 22.2% | Only Grok 4.20 measured |
| Furniture assembly | 26.7% | Not measured | Only Gemini 3.7 Flash measured |
| CL-bench Life | Not measured | 11.9% | Only Grok 4.20 measured |
| LMArena Text | 1489 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Text: instruction following | 1484 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Text: creative writing | 1488 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Vision | 1314 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Text: English | 1483 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Text: non-English | 1487 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Text: Chinese | 1552 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Text: German | 1506 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Text: Japanese | 1511 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Text: Korean | 1481 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Text: French | 1500 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Text: Spanish | 1495 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Text: Russian | 1515 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Text: Polish | 1503 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Text: multi-turn | 1485 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Text: longer queries | 1492 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Text: writing and language | 1491 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Text: entertainment and media | 1477 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Vision: English | 1309 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Vision: Chinese | 1394 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Vision: reading text | 1322 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Vision: humor | 1299 | Not measured | Only Gemini 3.7 Flash measured |
| LMArena Vision: creative writing | 1312 | Not measured | Only Gemini 3.7 Flash measured |
| Neither model has a result on the other 12 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | Gemini 3.7 Flash | Grok 4.20 | 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
Grok 4.20 costs less
Repository review
50K input + 3K output tokens
Gemini 3.7 Flash costs less
Agent loop
200K input + 10K output tokens
Gemini 3.7 Flash 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 Gemini 3.7 Flash | SpaceXAI Grok 4.20 |
|---|---|---|
| Maker | xAI | |
| Weights | No public weights listed | No public weights listed |
| Released | August 13, 2026 | March 31, 2026 |
| Context window | 1.05M | 2M |
| Input $/Mtok | $0.75 | $1.25 |
| Output $/Mtok | $3.75 | $2.50 |
| Coding index | 58.0 | 33.3 |
| Independent measurements behind it | 6 | 2 |
| Cost per solved task | $1.78 | $0.72 |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemini 3.7 Flash better than Grok 4.20 for coding?
Pick Gemini 3.7 Flash for coding: it scores 58.0 on the Vibe Coding Index against 33.3 for Grok 4.20. Pick Grok 4.20 for output tokens 1.5x cheaper ($2.50 vs $3.75 per million) and a lower cost per solved task ($0.72 against $1.78).
Which is cheaper, Gemini 3.7 Flash or Grok 4.20?
Gemini 3.7 Flash costs $0.75 per million input tokens and $3.75 per million output tokens; Grok 4.20 costs $1.25 and $2.50. Per solved SWE-bench Verified task, Gemini 3.7 Flash costs $1.78 and Grok 4.20 $0.72.
Which has the bigger context window, Gemini 3.7 Flash or Grok 4.20?
Grok 4.20, with 2M tokens against 1.05M.
How many benchmarks is the Gemini 3.7 Flash vs Grok 4.20 comparison based on?
40 benchmarks have a result for both models as of October 21, 2026. Gemini 3.7 Flash's coding index rests on 6 independent benchmarks and Grok 4.20's on 2. Where only one model has a result, the page says so instead of naming a winner.