Gemini 3.8 Flash vs gpt-oss-20b
Gemini 3.8 Flash leads gpt-oss-20b on the Artificial Analysis Intelligence Index, 40.9 to 10.0, and gpt-oss-20b costs 25.0x less per output token ($0.15 vs $3.75 per million). Updated October 21, 2026; 46 benchmarks have a result for both.
vs boards won of 46 shared
Gemini 3.8 Flash or gpt-oss-20b: which to pick
Only Gemini 3.8 Flash has a coding score, 61.6 on the Vibe Coding Index; gpt-oss-20b has none, so the two cannot be ranked on coding.
Pick gpt-oss-20b for output tokens 25.0x cheaper ($0.15 vs $3.75 per million).
Model AGemini 3.8 FlashGoogle61.6/1006 independent benchmarks$2.74 per solved taskModel Bgpt-oss-20bOpenAINot benchmarkedNo coding benchmarkNo cost per solved task
- Shared results
- 46
- Gemini 3.8 Flash only
- 82
- gpt-oss-20b only
- 16
- 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
No call
Only Gemini 3.8 Flash has a coding score, so no call is made.
One side not measured
Intelligence
AA Intelligence Index
Gemini 3.8 Flash
Gemini 3.8 Flash leads, 40.9 against 10.0.
Same board, both measured
Agentic work
AA Agentic Index
No call
Only Gemini 3.8 Flash has a AA Agentic Index result, 40.2.
Directional only
Reasoning
GPQA Diamond
Gemini 3.8 Flash
Gemini 3.8 Flash leads, 94.4% against 68.9%.
Same board, both measured
Math
AIME
No call
Only gpt-oss-20b has a AIME result, 86.0%.
Directional only
Knowledge
MMLU Pro
Gemini 3.8 Flash
Gemini 3.8 Flash leads, 90.2% against 71.6%.
Same board, both measured
Web design
Design Arena: websites
Gemini 3.8 Flash
Gemini 3.8 Flash leads, 1300 against 852.
Same board, both measured
General
Vals Index
No call
Only Gemini 3.8 Flash has a Vals Index result, 56.0%.
Directional only
Long documents
Listed context window
Gemini 3.8 Flash
Gemini 3.8 Flash takes 1.05M tokens against 131K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
gpt-oss-20b
Gemini 3.8 Flash $0.0026, gpt-oss-20b $0.0001 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only Gemini 3.8 Flash has the number, $2.74.
Directional only
At a glance
- Coding index
- Gemini 3.8 Flash 61.6 from 6 benchmarks, gpt-oss-20b not benchmarked.
- Widest category
- Web design, 49.0 points apart on average over 2 shared benchmarks.
- Widest single gap
- Design Arena: websites: Gemini 3.8 Flash 1300 against gpt-oss-20b 852, 56.0 points apart on a 0 to 100 scale.
- Output price
- Gemini 3.8 Flash $3.75 against gpt-oss-20b $0.15 per million output tokens, 25.0x apart.
- Context window
- Gemini 3.8 Flash takes 1.05M tokens, gpt-oss-20b 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 | Gemini 3.8 Flash | Bars | gpt-oss-20b | Ties |
|---|---|---|---|---|
| Coding | 6 | 0 | ||
| Intelligence | 2 | 0 | ||
| Reasoning | 7 | 0 | ||
| Math | 3 | 0 | ||
| Knowledge | 7 | 0 | ||
| Web design | 2 | 0 | ||
| General | 19 | 0 | ||
| All shared boards | 46 | 0 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index60
| Benchmark | Gemini 3.8 Flash | gpt-oss-20b | Leader |
|---|---|---|---|
| LiveBench coding | 82.2% | Not measured | Only Gemini 3.8 Flash measured |
| LMArena WebDev | 1585 | Not measured | Only Gemini 3.8 Flash measured |
| AA Coding Index | 76.3 | Not measured | Only Gemini 3.8 Flash measured |
| LiveCodeBench (Vals AI) | 89.5% | 80.4% | Gemini 3.8 Flash |
| SWE-bench Verified (Vals AI) | 80.0% | Not measured | Only Gemini 3.8 Flash measured |
| Terminal-Bench 4 (Vals AI) | 19.7% | Not measured | Only Gemini 3.8 Flash measured |
| Vibe Code Bench (Vals AI) | 78.7% | Not measured | Only Gemini 3.8 Flash measured |
| Code migration (Vals AI) | 36.5% | Not measured | Only Gemini 3.8 Flash measured |
| ProgramBench (Vals AI) | 1.0% | Not measured | Only Gemini 3.8 Flash measured |
| IOI (Vals AI) | 56.9% | Not measured | Only Gemini 3.8 Flash measured |
| Terminal-Bench 2.1 (Vals AI) | 81.3% | Not measured | Only Gemini 3.8 Flash measured |
| SWE-bench Multimodal (Vals AI) | 40.8% | Not measured | Only Gemini 3.8 Flash measured |
| Vibe Code Bench 1-100 (Vals AI) | 18.8% | Not measured | Only Gemini 3.8 Flash measured |
| SkillsBench (Vals AI) | 58.0% | Not measured | Only Gemini 3.8 Flash measured |
| CyberBench (Vals AI) | 43.8% | Not measured | Only Gemini 3.8 Flash measured |
| LiveCodeBench (Artificial Analysis run) | Not measured | 77.7% | Only gpt-oss-20b measured |
| SciCode | 56.6% | 38.9% | Gemini 3.8 Flash |
| Terminal-Bench Hard (Artificial Analysis run) | Not measured | 10.6% | Only gpt-oss-20b measured |
| Terminal-Bench | Not measured | 3.4% | Only gpt-oss-20b measured |
| FrontierCode | 41.2% | Not measured | Only Gemini 3.8 Flash measured |
| FrontierSWE | 19.6% | Not measured | Only Gemini 3.8 Flash measured |
| WeirdML | 84.8% | 40.9% | Gemini 3.8 Flash |
| ALE-Bench | 1269.7 | 566.0 | Gemini 3.8 Flash |
| LMArena Text: coding | 1508 | 1307 | Gemini 3.8 Flash |
| LMArena Text: software and IT | 1507 | 1311 | Gemini 3.8 Flash |
| LMArena WebDev: React | 1577 | Not measured | Only Gemini 3.8 Flash measured |
| LMArena WebDev: HTML | 1616 | Not measured | Only Gemini 3.8 Flash measured |
| LMArena WebDev: from an image | 1593 | Not measured | Only Gemini 3.8 Flash measured |
| SciCode | 12.3% | Not measured | Only Gemini 3.8 Flash measured |
| Neither model has a result on the other 10 boards here | |||
IntelligenceLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Gemini 3.8 Flash | gpt-oss-20b | Leader |
|---|---|---|---|
| AA Intelligence Index | 40.9 | 10.0 | Gemini 3.8 Flash |
| Epoch Capabilities Index | 157.4 | 137.7 | Gemini 3.8 Flash |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index27 boards, none shared
| Benchmark | Gemini 3.8 Flash | gpt-oss-20b | Leader |
|---|---|---|---|
| AA Agentic Index | 40.2 | Not measured | Only Gemini 3.8 Flash measured |
| Design Arena: agents building web apps | 1238 | Not measured | Only Gemini 3.8 Flash measured |
| Design Arena: agents building full-stack apps | 1244 | Not measured | Only Gemini 3.8 Flash measured |
| Design Arena: agents building mobile apps | 1236 | Not measured | Only Gemini 3.8 Flash measured |
| Design Arena: agents building Android apps | 1074 | Not measured | Only Gemini 3.8 Flash measured |
| Design Arena: agents building Godot games | 1273 | Not measured | Only Gemini 3.8 Flash measured |
| Design Arena: PowerPoint slides | 1177 | Not measured | Only Gemini 3.8 Flash measured |
| Design Arena: spreadsheets | 1056 | Not measured | Only Gemini 3.8 Flash measured |
| LiveBench research | 79.1% | Not measured | Only Gemini 3.8 Flash measured |
| LiveBench browser | 64.0% | Not measured | Only Gemini 3.8 Flash measured |
| LiveBench long agentic | 30.1% | Not measured | Only Gemini 3.8 Flash measured |
| SREBench (Vals AI) | 11.1% | Not measured | Only Gemini 3.8 Flash measured |
| Finance Agent (Vals AI) | 61.4% | Not measured | Only Gemini 3.8 Flash measured |
| Tax Agent Bench (Vals AI) | 32.1% | Not measured | Only Gemini 3.8 Flash measured |
| Legal Research Bench (Vals AI) | 38.9% | Not measured | Only Gemini 3.8 Flash measured |
| Harvey's Legal Agent Benchmark (Vals AI) | 12.1% | Not measured | Only Gemini 3.8 Flash measured |
| Excel Modeling Benchmark (Vals AI) | 72.2% | Not measured | Only Gemini 3.8 Flash measured |
| BioMysteryBench (Vals AI) | 62.2% | Not measured | Only Gemini 3.8 Flash measured |
| Terminal-Bench-Science (Vals AI) | 8.6% | Not measured | Only Gemini 3.8 Flash measured |
| Vals Science Index | 35.8% | Not measured | Only Gemini 3.8 Flash measured |
| Time Horizon Index (Vals AI) | 18.8% | Not measured | Only Gemini 3.8 Flash measured |
| CUA-bench (Vals AI) | 4.2% | Not measured | Only Gemini 3.8 Flash measured |
| τ²-Bench Telecom | Not measured | 60.2% | Only gpt-oss-20b measured |
| APEX-Agents | 64.3% | Not measured | Only Gemini 3.8 Flash measured |
| Remote Labor Index | 5.8% | Not measured | Only Gemini 3.8 Flash measured |
| Vending-Bench 2 | $5,094 | Not measured | Only Gemini 3.8 Flash measured |
| BrowseComp-Plus | Not measured | 50.6% | Only gpt-oss-20b measured |
| Neither model has a result on the other 14 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index70
| Benchmark | Gemini 3.8 Flash | gpt-oss-20b | Leader |
|---|---|---|---|
| GPQA Diamond | 94.4% | 68.9% | Gemini 3.8 Flash |
| LiveBench reasoning | 89.3% | Not measured | Only Gemini 3.8 Flash measured |
| MysteryMechanism (Vals AI) | 36.5% | Not measured | Only Gemini 3.8 Flash measured |
| MMMU Pro (Vals AI) | 89.1% | Not measured | Only Gemini 3.8 Flash measured |
| GPQA Diamond (Artificial Analysis run) | 95.3% | 68.8% | Gemini 3.8 Flash |
| Humanity's Last Exam (Artificial Analysis run) | 47.8% | 11.0% | Gemini 3.8 Flash |
| GPQA Diamond (Epoch AI run) | 95.4% | 60.8% | Gemini 3.8 Flash |
| ARC-AGI | 98.5% | Not measured | Only Gemini 3.8 Flash measured |
| ARC-AGI-2 | 89.2% | Not measured | Only Gemini 3.8 Flash measured |
| Chess puzzles | 58.0% | Not measured | Only Gemini 3.8 Flash measured |
| Mystery game puzzles | 47.0% | Not measured | Only Gemini 3.8 Flash measured |
| LMArena Text: hard prompts | 1509 | 1274 | Gemini 3.8 Flash |
| LMArena Text: expert | 1526 | 1258 | Gemini 3.8 Flash |
| LMArena Text: hard prompts in English | 1504 | 1292 | Gemini 3.8 Flash |
| LMArena Vision: diagrams | 1345 | Not measured | Only Gemini 3.8 Flash measured |
| LMArena Vision: homework | 1351 | Not measured | Only Gemini 3.8 Flash measured |
| Kagi LLM Benchmark | Not measured | 53.2% | Only gpt-oss-20b measured |
| Neither model has a result on the other 5 boards here | |||
MathLike-for-likePublic boards, shown as published, kept out of the index30
| Benchmark | Gemini 3.8 Flash | gpt-oss-20b | Leader |
|---|---|---|---|
| AIME | Not measured | 86.0% | Only gpt-oss-20b measured |
| MATH 500 (Vals AI) | Not measured | 94.2% | Only gpt-oss-20b measured |
| MGSM (Vals AI) | Not measured | 89.0% | Only gpt-oss-20b measured |
| AA Math Index | Not measured | 89.3 | Only gpt-oss-20b measured |
| AIME 2025 (Artificial Analysis run) | Not measured | 89.3% | Only gpt-oss-20b measured |
| OTIS Mock AIME | 98.9% | 65.3% | Gemini 3.8 Flash |
| FrontierMath, tiers 1 to 3 | 68.4% | Not measured | Only Gemini 3.8 Flash measured |
| FrontierMath, tier 4 | 22.0% | Not measured | Only Gemini 3.8 Flash measured |
| ProofBench | 48.0% | Not measured | Only Gemini 3.8 Flash measured |
| LMArena Text: math | 1532 | 1317 | Gemini 3.8 Flash |
| LMArena Text: mathematical work | 1519 | 1305 | Gemini 3.8 Flash |
| Neither model has a result on the other 2 boards here | |||
KnowledgeLike-for-likePublic boards, shown as published, kept out of the index70
| Benchmark | Gemini 3.8 Flash | gpt-oss-20b | Leader |
|---|---|---|---|
| MMLU Pro | 90.2% | 71.6% | Gemini 3.8 Flash |
| LegalBench (Vals AI) | 87.0% | 70.8% | Gemini 3.8 Flash |
| CaseLaw (Vals AI) | Not measured | 43.8% | Only gpt-oss-20b measured |
| CorpFin (Vals AI) | Not measured | 53.1% | Only gpt-oss-20b measured |
| TaxEval (Vals AI) | 74.5% | 63.7% | Gemini 3.8 Flash |
| MortgageTax (Vals AI) | 65.3% | Not measured | Only Gemini 3.8 Flash measured |
| MedQA (Vals AI) | Not measured | 82.9% | Only gpt-oss-20b measured |
| MedCode (Vals AI) | 48.1% | Not measured | Only Gemini 3.8 Flash measured |
| MMLU Pro (Artificial Analysis run) | Not measured | 74.8% | Only gpt-oss-20b measured |
| SimpleQA Verified | 69.7% | Not measured | Only Gemini 3.8 Flash measured |
| LMArena Text: science | 1523 | 1296 | Gemini 3.8 Flash |
| LMArena Text: medicine and healthcare | 1508 | 1310 | Gemini 3.8 Flash |
| LMArena Text: legal and government | 1497 | 1280 | Gemini 3.8 Flash |
| LMArena Text: business and finance | 1479 | 1284 | Gemini 3.8 Flash |
| FACTS Benchmark Suite | 69.4% | Not measured | Only Gemini 3.8 Flash measured |
| Neither model has a result on the other 3 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index20
| Benchmark | Gemini 3.8 Flash | gpt-oss-20b | Leader |
|---|---|---|---|
| Design Arena: websites | 1300 | 852 | Gemini 3.8 Flash |
| Design Arena: UI components | 1319 | Not measured | Only Gemini 3.8 Flash measured |
| Design Arena: game dev | 1305 | Not measured | Only Gemini 3.8 Flash measured |
| Design Arena: data viz | 1269 | 933 | Gemini 3.8 Flash |
| Design Arena: 3D | 1295 | Not measured | Only Gemini 3.8 Flash measured |
| Design Arena: all code categories | 1304 | Not measured | Only Gemini 3.8 Flash measured |
| Design Arena: SVG | 1295 | Not measured | Only Gemini 3.8 Flash measured |
| Design Arena: ASCII art | 1265 | Not measured | Only Gemini 3.8 Flash measured |
| LiveBench design | 72.7% | Not measured | Only Gemini 3.8 Flash measured |
GeneralLike-for-likePublic boards, shown as published, kept out of the index190
| Benchmark | Gemini 3.8 Flash | gpt-oss-20b | Leader |
|---|---|---|---|
| Vals Index | 56.0% | Not measured | Only Gemini 3.8 Flash measured |
| LiveBench data analysis | 54.0% | Not measured | Only Gemini 3.8 Flash measured |
| Public Benefits Bench (Vals AI) | 65.3% | Not measured | Only Gemini 3.8 Flash measured |
| SAGE (Vals AI) | 35.1% | Not measured | Only Gemini 3.8 Flash measured |
| MedScribe (Vals AI) | 84.5% | Not measured | Only Gemini 3.8 Flash measured |
| IFBench | Not measured | 65.1% | Only gpt-oss-20b measured |
| Long context reasoning (AA-LCR) | 84.0% | 34.7% | Gemini 3.8 Flash |
| DTBench | 95.7% | 68.0% | Gemini 3.8 Flash |
| LMCA | 52.9% | 14.5% | Gemini 3.8 Flash |
| Surface Evolver Bench | 76.9% | Not measured | Only Gemini 3.8 Flash measured |
| Furniture assembly | 31.7% | Not measured | Only Gemini 3.8 Flash measured |
| LMArena Text | 1499 | 1288 | Gemini 3.8 Flash |
| LMArena Text: instruction following | 1492 | 1236 | Gemini 3.8 Flash |
| LMArena Text: creative writing | 1488 | 1201 | Gemini 3.8 Flash |
| LMArena Vision | 1315 | Not measured | Only Gemini 3.8 Flash measured |
| LMArena Text: English | 1498 | 1303 | Gemini 3.8 Flash |
| LMArena Text: non-English | 1491 | 1269 | Gemini 3.8 Flash |
| LMArena Text: Chinese | 1553 | 1315 | Gemini 3.8 Flash |
| LMArena Text: German | 1501 | 1255 | Gemini 3.8 Flash |
| LMArena Text: Japanese | 1507 | 1244 | Gemini 3.8 Flash |
| LMArena Text: Korean | 1464 | 1236 | Gemini 3.8 Flash |
| LMArena Text: French | 1496 | Not measured | Only Gemini 3.8 Flash measured |
| LMArena Text: Spanish | 1487 | 1267 | Gemini 3.8 Flash |
| LMArena Text: Russian | 1514 | 1278 | Gemini 3.8 Flash |
| LMArena Text: Polish | 1497 | 1252 | Gemini 3.8 Flash |
| LMArena Text: multi-turn | 1503 | 1268 | Gemini 3.8 Flash |
| LMArena Text: longer queries | 1507 | 1250 | Gemini 3.8 Flash |
| LMArena Text: writing and language | 1494 | 1238 | Gemini 3.8 Flash |
| LMArena Text: entertainment and media | 1480 | 1216 | Gemini 3.8 Flash |
| LMArena Vision: English | 1318 | Not measured | Only Gemini 3.8 Flash measured |
| LMArena Vision: Chinese | 1416 | Not measured | Only Gemini 3.8 Flash measured |
| LMArena Vision: reading text | 1333 | Not measured | Only Gemini 3.8 Flash measured |
| LMArena Vision: humor | 1321 | Not measured | Only Gemini 3.8 Flash measured |
| LMArena Vision: creative writing | 1299 | Not measured | Only Gemini 3.8 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 3.8 Flash | gpt-oss-20b | 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 3.8 Flash$0.0026Fits in one request
gpt-oss-20b$0.0001Fits in one request
gpt-oss-20b costs less
Repository review
50K input + 3K output tokens
Gemini 3.8 Flash$0.049Fits in one request
gpt-oss-20b$0.0019Fits in one request
gpt-oss-20b costs less
Agent loop
200K input + 10K output tokens
Gemini 3.8 Flash$0.188Fits in one request
gpt-oss-20b$0.0075Exceeds the context window
gpt-oss-20b 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 3.8 Flash | OpenAI gpt-oss-20b |
|---|---|---|
| Maker | OpenAI | |
| Weights | No public weights listed | Open weights |
| Released | September 2, 2026 | August 5, 2025 |
| Context window | 1.05M | 131K |
| Input $/Mtok | $0.75 | $0.03 |
| Output $/Mtok | $3.75 | $0.15 |
| Coding index | 61.6 | Not benchmarked |
| Independent measurements behind it | 6 | 0 |
| Cost per solved task | $2.74 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is Gemini 3.8 Flash better than gpt-oss-20b for coding?
Only Gemini 3.8 Flash has a coding score, 61.6 on the Vibe Coding Index; gpt-oss-20b has none, so the two cannot be ranked on coding. Pick gpt-oss-20b for output tokens 25.0x cheaper ($0.15 vs $3.75 per million).
Which is cheaper, Gemini 3.8 Flash or gpt-oss-20b?
Gemini 3.8 Flash costs $0.75 per million input tokens and $3.75 per million output tokens; gpt-oss-20b costs $0.03 and $0.15. Cost per solved task is known for Gemini 3.8 Flash only.
Which has the bigger context window, Gemini 3.8 Flash or gpt-oss-20b?
Gemini 3.8 Flash, with 1.05M tokens against 131K.
How many benchmarks is the Gemini 3.8 Flash vs gpt-oss-20b comparison based on?
46 benchmarks have a result for both models as of October 21, 2026. Gemini 3.8 Flash's coding index rests on 6 independent benchmarks and gpt-oss-20b's on 0. Where only one model has a result, the page says so instead of naming a winner.