Across 9 comparable benchmarks, Gemini 3.1 Flash-Lite has better reported results on 7 and worse on 2.
Moderate evidence9 of 9 shared results countedHow we compare
Price basis: Standard rates. The price section below shows the applicable periods.
| Fact | gpt-oss-20b | Gemini 3.1 Flash-Lite |
|---|---|---|
| Context window | 128K tokens | 1M tokens |
| Input / 1M | $0.030 | $0.250 |
| Output / 1M | $0.140 | $1.50 |
| Blended (4:1) | $0.052 | $0.338 |
| Status | Available | Deprecated |
| Released | August 6, 2025 | May 7, 2026 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 4 shared benchmarks grouped by capability on a 0–100 scale. How averages are built
Gemini 3.1 Flash-Lite ahead on 1 of 1 counted
Gemini 3.1 Flash-Lite ahead on 2 of 3 counted
Gemini 3.1 Flash-Lite ahead on 1 of 1 counted
Gemini 3.1 Flash-Lite ahead on 1 of 1 counted
Gemini 3.1 Flash-Lite ahead on 1 of 1 counted
No fixed-scale average — see the rows in Benchmark results
No shared comparable results for Abstract reasoning, Mathematics, Research & search, Long context, Cybersecurity.
Published scores, with matching modes where available. Gaps show gpt-oss-20b relative to Gemini 3.1 Flash-Lite. Reading the results
| Benchmark | gpt-oss-20b | Gemini 3.1 Flash-Lite | Gap |
|---|---|---|---|
| Terminal Bench HardAgentic Development · Accuracy | 10.6Thinking High · tools | 24.2≠Thinking · tools | −13.6 pts#115 vs #83 of 157 |
| CritPtScientific Reasoning · Score | 1.4Thinking High · no tools | 1.1≠Thinking · no tools | 1.27×#96 vs #103 of 134 |
| GPQA DiamondScientific Reasoning · Accuracy | 71.5Thinking · no tools | 81.8≠Thinking High · no tools | −10.3 pts#130 vs #100 of 200 |
| SciCodeScientific Computing · Score | 38.9Thinking High · no tools | 43.4≠Thinking · no tools | 0.90×#79 vs #69 of 98 |
| PinchBench v2Tool Orchestration · Average score (%) | 36.3Reported best | 80.5Reported best | −44.2 pts#48 vs #14 of 51 |
| GDP.pdfDocuments & Charts · Task pass rate (%) | 2.0Thinking High · no tools | 7.8≠Thinking · no tools | −5.8 pts#84 vs #67 of 96 |
| τ³-BankingService Workflows · Score | 7.0Thinking High · tools | 9.7≠Thinking · tools | 0.72×#99 vs #94 of 120 |
| HLEKnowledge Exams · Accuracy | 17.3Thinking · tools | 8.6≠Reported best | +8.7 pts#114 vs #133 of 151 |
| ECICapability Indices · ECI score (capability index, higher is better) | 138Reported best | 144Reported best | 0.95×#106 vs #81 of 168 |
Agentic Development · Accuracy
Scientific Reasoning · Score
Scientific Reasoning · Accuracy
Scientific Computing · Score
Tool Orchestration · Average score (%)
Documents & Charts · Task pass rate (%)
Service Workflows · Score
A dash means no result is available.
| Benchmark | gpt-oss-20b | Gemini 3.1 Flash-Lite |
|---|---|---|
| AIME 2024 | 96.0 | — |
| AIME2025 | 98.7 | — |
| FrontierMath v2 | — | 27.7 |
| MMLU | 85.3 | — |
| MMLU-Pro | 74.0 | — |
| Code Migration | — | 4.6 |
| CodeForces | 2516 | — |
| SWE-bench Verified | 34.0 | — |
| Terminal-Bench 4.0 | — | 0.5 |
| Vibe Code Bench v1.1 | — | 0.0 |
| MCP-Atlas | — | 57.1 |
| Pinch Bench | 66.0 | — |
| AA Intelligence Index v5.0.1 | — | 6.2 |
| LiveBench | — | 61.7 |
| Vals Index | — | 15.5 |
| Creative Writing | 665 | — |
| MMMU-Pro | — | 75.5 |
| AA-AnalystAgent | — | 8.8 |
| EMB (Excel Modeling) | — | 8.6 |
| Finance Agent v2 | — | 30.0 |
| Harvey Lab-AA | — | 31.1 |
| Harvey's Legal Agent Benchmark | — | 0.0 |
| Legal Research Bench | — | 3.4 |
| SAGE | — | 49.5 |
| τ²-Bench | 47.7 | — |
| BrowseComp | 28.3 | — |
| MedCode | — | 47.6 |
| MedScribe | — | 63.9 |
Time-of-day providers use peak-hour rates; fixed-price providers use standard rates. Off-peak discounts remain in the published details.
Drag the handle above the bar for cache hits, the one below it for the input : output mix · 5% steps
Blended price = effective input rate at 90% cache hits × 80% + output rate × 20%
gpt-oss-20b costs85%lessthan Gemini 3.1 Flash-Lite per million tokens — 6.5× cheaper.Using standard rates at this token mix.
gpt-oss-20b: Standard pricing. DeepInfra official models API (openai/gpt-oss-20b) verified 2026-11-13
Gemini 3.1 Flash-Lite: Standard pricing. Google Gemini API official pricing (ai.google.dev/gemini-api/docs/pricing) verified 2026-10-21; paid tier; standard tier
| Price / 1M tokens | gpt-oss-20b | Gemini 3.1 Flash-Lite | Ratio |
|---|---|---|---|
| Input | $0.03 | $0.25 | 0.12× |
| Output | $0.14 | $1.50 | 0.09× |
| Cached input | — | $0.025 | — |
| Cache write | — | — | — |
| Blended | $0.052 | $0.338 | 0.15× |
Estimates use the selected token mix. Cache writes, tool fees and long-context surcharges are excluded.
Reported cost per task, paired with the score from the same run. Settings and sources may differ; costs do not affect the verdict.
| Benchmark | gpt-oss-20b | Gemini 3.1 Flash-Lite |
|---|---|---|
| AA Intelligence Index v5.0.1 | Not reported |
| Attribute | gpt-oss-20b | Gemini 3.1 Flash-Lite |
|---|---|---|
| Availability | Available | Deprecated |
| Provider | OpenAI | Google Deep Mind |
| Model type | Reasoning model | Multimodal model |
| First release | August 6, 2025 | May 7, 2026 |
| Context window | 128K tokens | 1M tokens |
| Max output | 128K tokens | 66K tokens |
| Total parameters | 21B | — |
| Active parameters | 3.6B | — |
| Architecture | Mixture of Experts (MoE) | Undisclosed |
| Documented capabilities | Reasoning, Multilingual | Reasoning, Multilingual, Tool use, Long context |
| Knowledge cutoff | — | 2025-01 |
| Input modalities | Text | Text, Image, Audio, Video |
| Output modalities | Text | Text |
| Weights | Open weights | Closed / API only |
| Licence | Apache 2.0 | — |
| Commercial use | Commercial use allowed | Proprietary |
These are reported-score comparisons, not controlled head-to-head tests.
What people found comparing these models, or using either one. Comments also appear on the models' own pages.
Used gpt-oss-20b or Gemini 3.1 Flash-Lite? Sign in with Google to share what worked, what did not, and which API or setup you tested.
No community comments on either model yet.
Alternatives with the most benchmark overlap for this matchup.