Across 12 comparable benchmarks, Gemini 3.1 Flash-Lite has better reported results on 9 and worse on 2, with 1 tied.
Moderate evidence12 of 12 shared results countedHow we compare
Price basis: Standard rates. The price section below shows the applicable periods.
| Fact | Gemini 3.1 Flash-Lite | GPT OSS 120B |
|---|---|---|
| Context window | 1M tokens | 128K tokens |
| Input / 1M | $0.250 | $0.350 |
| Output / 1M | $1.50 | $0.750 |
| Blended (4:1) | $0.338 | $0.430 |
| Status | Deprecated | Available |
| Released | May 7, 2026 | August 6, 2025 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 5 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
Split 1–1 of 2 counted
No shared comparable results for Abstract reasoning, Mathematics, Research & search, Long context, Cybersecurity.
Published scores, with matching modes where available. Gaps show Gemini 3.1 Flash-Lite relative to GPT OSS 120B. Reading the results
| Benchmark | Gemini 3.1 Flash-Lite | GPT OSS 120B | Gap |
|---|---|---|---|
| Terminal Bench HardAgentic Development · Accuracy | 24.2Thinking · tools | 23.5≠Thinking High · tools | +0.7 pts#83 vs #88 of 157 |
| CritPtScientific Reasoning · Score | 1.1Thinking · no tools | 1.1≠Thinking High · no tools | =#103 vs #103 of 134 |
| GPQA DiamondScientific Reasoning · Accuracy | 81.8Thinking High · no tools | 80.1≠Thinking · no tools | +1.7 pts#100 vs #111 of 200 |
| SciCodeScientific Computing · Score | 43.4Thinking · no tools | 34.0≠Thinking High · no tools | 1.28×#69 vs #88 of 98 |
| PinchBench v2Tool Orchestration · Average score (%) | 80.5Reported best | 44.8Reported best | +35.7 pts#14 vs #46 of 51 |
| GDP.pdfDocuments & Charts · Task pass rate (%) | 7.8Thinking · no tools | 4.0≠Thinking High · no tools | +3.8 pts#67 vs #77 of 96 |
| Harvey Lab-AALegal · Criterion pass rate (some entries report all-pass rate) | 31.1Thinking · tools | 13.9≠Thinking High · tools | +17.3 pts#36 vs #39 of 39 |
| τ³-BankingService Workflows · Score | 9.7Thinking · tools | 12.8≠Thinking High · tools | 0.76×#94 vs #83 of 120 |
| HLEKnowledge Exams · Accuracy | 8.6Reported best | 19.0≠Thinking · tools | −10.4 pts#133 vs #107 of 151 |
| AA Intelligence Index v5.0.1Capability Indices · Index (0-100) | 6.2Thinking High · tools | 3.8Thinking High · tools | 1.61×#57 vs #62 of 62 |
| ECICapability Indices · ECI score (capability index, higher is better) | 144Reported best | 140Reported best | 1.03×#81 vs #97 of 168 |
| LiveBenchCross-capability Suites · Accuracy | 61.7Thinking High · no tools | 46.1≠Normal · no tools | +15.6 pts#79 vs #100 of 106 |
Agentic Development · Accuracy
Scientific Reasoning · Score
Scientific Reasoning · Accuracy
Scientific Computing · Score
Tool Orchestration · Average score (%)
Documents & Charts · Task pass rate (%)
Legal · Criterion pass rate (some entries report all-pass rate)
Service Workflows · Score
A dash means no result is available.
| Benchmark | Gemini 3.1 Flash-Lite | GPT OSS 120B |
|---|---|---|
| AIME 2024 | — | 96.6 |
| AIME2025 | — | 97.9 |
| FrontierMath v2 | 27.7 | — |
| MathArena Apex | — | 1.0 |
| MMLU | — | 90.0 |
| MMLU-Pro | — | 79.0 |
| Aider-Polyglot | — | 41.8 |
| APEX-SWE | — | 3.3 |
| Code Migration | 4.6 | — |
| CodeForces | — | 2622 |
| LiveCodeBench | — | 87.8 |
| SWE-bench Verified | — | 60.1 |
| Terminal-Bench 4.0 | 0.5 | — |
| Vibe Code Bench v1.1 | 0.0 | — |
| APEX-Agents | — | 4.4 |
| MCP-Atlas | 57.1 | — |
| Pinch Bench | — | 60.6 |
| AA Intelligence Index (historical versions) | — | 24.1 |
| Vals Index | 15.5 | — |
| Creative Writing | — | 956 |
| IF Bench | — | 69.0 |
| MMMU-Pro | 75.5 | — |
| AA-AnalystAgent | 8.8 | — |
| AutomationBench | — | 0.15 |
| EMB (Excel Modeling) | 8.6 | — |
| Finance Agent v2 | 30.0 | — |
| Harvey's Legal Agent Benchmark | 0.0 | — |
| Legal Research Bench | 3.4 | — |
| SAGE | 49.5 | — |
| SimpleBench | — | 22.1 |
| Vending-Bench 2 | — | -21.5 |
| 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%
Gemini 3.1 Flash-Lite costs21%lessthan GPT OSS 120B per million tokens.Using standard rates at this token mix.
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
GPT OSS 120B: Standard pricing. Cerebras Shared Inference official pricing (gpt-oss-120b) verified 2026-11-13
| Price / 1M tokens | Gemini 3.1 Flash-Lite | GPT OSS 120B | Ratio |
|---|---|---|---|
| Input | $0.25 | $0.35 | 0.71× |
| Output | $1.50 | $0.75 | 2.00× |
| Cached input | $0.025 | — | — |
| Cache write | — | — | — |
| Blended | $0.338 | $0.43 | 0.79× |
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.
Gemini 3.1 Flash-Lite relative to GPT OSS 120B
Summary: 1 of 1 shared benchmarks have matching recorded settings and sources. The average is a geometric mean of 1 positive-cost ratios, one equal weight per benchmark. This benchmark set can include related tests and indexes; it is not a workload cost estimate.
Gemini 3.1 Flash-Lite 1.8× cheaper
Gemini 3.1 Flash-Lite 1.8× cheaper
Effort, protocol, aggregation and source match; other run conditions may differ.
Gemini 3.1 Flash-Lite
GPT OSS 120B
| Benchmark | Gemini 3.1 Flash-Lite | GPT OSS 120B |
|---|---|---|
| AutomationBench | Not reported | $0.01 / task Average · Pass Rate: 0.15 Thinking High (With Tools) · zapier-private-heldout |
| Attribute | Gemini 3.1 Flash-Lite | GPT OSS 120B |
|---|---|---|
| Availability | Deprecated | Available |
| Provider | Google Deep Mind | OpenAI |
| Model type | Multimodal model | Reasoning model |
| First release | May 7, 2026 | August 6, 2025 |
| Context window | 1M tokens | 128K tokens |
| Max output | 66K tokens | 128K tokens |
| Total parameters | — | 117B |
| Active parameters | — | 5.1B |
| Architecture | Undisclosed | Mixture of Experts (MoE) |
| Documented capabilities | Reasoning, Multilingual, Tool use, Long context | Reasoning, Multilingual |
| Knowledge cutoff | 2025-01 | — |
| Input modalities | Text, Image, Audio, Video | Text |
| Output modalities | Text | Text |
| Weights | Closed / API only | Open weights |
| Licence | — | Apache 2.0 |
| Commercial use | Proprietary | Commercial use allowed |
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 Gemini 3.1 Flash-Lite or GPT OSS 120B? 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.