Across 11 comparable benchmarks, GPT-5.1 has better reported results on 6 and worse on 4, with 1 tied. 1 further shared result is listed below, each with the reason it is not counted.
Strong evidence11 of 12 shared results countedHow we compare
Price basis: Standard rates. The price section below shows the applicable periods.
| Fact | GPT-5.1 | Gemini 3.5 Flash-Lite |
|---|---|---|
| Context window | 400K tokens | 1M tokens |
| Input / 1M | $1.25 | $0.300 |
| Output / 1M | $10.00 | $2.50 |
| Blended (4:1) | $2.19 | $0.546 |
| Status | Deprecated | Available |
| Released | November 12, 2025 | July 21, 2026 |
Blended is 4:1 input to output with 90% cache hits at listed rates — set your own mix.
Mean of 8 shared benchmarks grouped by capability on a 0–100 scale. How averages are built
Gemini 3.5 Flash-Lite ahead on 2 of 2 counted
GPT-5.1 ahead on 1 of 1 counted
GPT-5.1 ahead on 3 of 3 counted
Tied on 1 counted
Gemini 3.5 Flash-Lite ahead on 2 of 2 counted
No shared comparable results for Mathematics, Computer & tool use, Research & search, Long context, Cybersecurity.
Published scores, with matching modes where available. Gaps show GPT-5.1 relative to Gemini 3.5 Flash-Lite. Reading the results
| Benchmark | GPT-5.1 | Gemini 3.5 Flash-Lite | Gap |
|---|---|---|---|
| SWE-Bench Pro - PublicRepository Engineering · Accuracy | 50.8Thinking High · no tools | 54.2≠Thinking · tools | −3.4 pts#48 vs #38 of 66 |
| Vibe Code Bench v1.1Code Generation & Editing · Pass rate (%) | 24.6Thinking High · tools | 37.2Thinking High · tools | −12.5 pts#82 vs #75 of 121 |
| ARC-AGI-1Abstract Generalization · Score (%) | 72.8Thinking High · no tools | 53.5≠Thinking High · tools | +19.3 pts#51 vs #65 of 87 |
| ARC-AGI-2Abstract Generalization · Score (% solved); cost per task (USD)Not counted · Speed and cost telemetry is reported, not scored | 17.6Thinking High · no tools | 10.3≠Thinking High · tools | 1.72×#55 vs #59 of 80 |
| GPQA DiamondScientific Reasoning · Accuracy | 88.1Thinking · no tools | 83.3≠Thinking High · no tools | +4.8 pts#65 vs #93 of 200 |
| MedCodeClinical Workflows · Accuracy (%) | 52.7Thinking High · tools | 43.5Thinking High · tools | +9.2 pts#13 vs #42 of 97 |
| MedScribeClinical Workflows · Rubric pass rate (%) | 88.1Thinking High · tools | 70.9Thinking High · tools | +17.2 pts#14 vs #85 of 99 |
| MMMU-ProVisual Understanding · Accuracy | 79.0Thinking · no tools | 79.0Thinking · no tools | =#38 vs #38 of 136 |
| SAGEService Workflows · Accuracy (%) | 43.2Thinking High · tools | 47.3Thinking High · tools | −4.1 pts#51 vs #32 of 82 |
| τ³-BankingService Workflows · Score | 15.9Thinking High · tools | 17.5≠Thinking · tools | 0.91×#69 vs #64 of 120 |
| ECICapability Indices · ECI score (capability index, higher is better) | 150Reported best | 145Reported best | 1.03×#51 vs #78 of 168 |
| LiveBenchCross-capability Suites · Accuracy | 72.0Thinking High · no tools | 63.9Thinking High · no tools | +8.1 pts#50 vs #73 of 106 |
Repository Engineering · Accuracy
Code Generation & Editing · Pass rate (%)
Scientific Reasoning · Accuracy
Clinical Workflows · Accuracy (%)
Clinical Workflows · Rubric pass rate (%)
Visual Understanding · Accuracy
Service Workflows · Accuracy (%)
Service Workflows · Score
A dash means no result is available.
| Benchmark | GPT-5.1 | Gemini 3.5 Flash-Lite |
|---|---|---|
| AIME2025 | 94.2 | — |
| CritPt | 4.9 | — |
| FrontierMath | 26.7 | — |
| FrontierMath - Tier 4 | 12.5 | — |
| FrontierMath Tier 4 v2 | — | 0.0 |
| FrontierMath v2 | — | 26.0 |
| HLE | 42.7 | — |
| IMO-ProofBench Advanced | 7.1 | — |
| MathArena Apex | 1.0 | — |
| MMLU-Pro | 87.0 | — |
| Riemann-bench | — | 11.2 |
| SciCode | — | 41.3 |
| APEX-SWE | — | 31.2 |
| Code Migration | — | 6.2 |
| GSO | 13.7 | — |
| IC SWE-Lancer (Diamond) | 69.7 | — |
| LiveCodeBench | 86.8 | — |
| SWE-bench Verified | 76.3 | — |
| SWE-sweep | — | 0.12 |
| Terminal Bench 2.0 | 47.6 | — |
| Terminal Bench Hard | 45.5 | — |
| Terminal-Bench 2.1 | — | 54.0 |
| Terminal-Bench 4.0 | — | 1.0 |
| WeirdML v2 | 60.8 | — |
| APEX-Agents | — | 29.3 |
| MCP-Atlas | 50.1 | — |
| OSWorld-Verified | — | 74.0 |
| Toolathlon-Verified | — | 57.1 |
| AA Intelligence Index v5.0.1 | — | 11.7 |
| Text Arena (Coding) | 1387 | — |
| Vals Index | — | 36.7 |
| Creative Writing | — | 1559 |
| Context Arena | — | 72.6 |
| GDP.pdf | — | 13.6 |
| MMMU | 85.4 | — |
| VPCT | 58.7 | — |
| AutomationBench | — | 4.0 |
| EMB (Excel Modeling) | — | 43.2 |
| Finance Agent v2 | — | 47.4 |
| Harvey's Legal Agent Benchmark | — | 0.0 |
| Legal Research Bench | — | 13.9 |
| Public Benefits Bench v1.1 | — | 51.8 |
| Tax Agent Bench | — | 7.3 |
| SimpleBench | 53.2 | — |
| Vending-Bench 2 | 1473 | — |
| BrowseComp | 50.8 | — |
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-5.1 costs301%morethan Gemini 3.5 Flash-Lite per million tokens — 4× the price.Using standard rates at this token mix.
GPT-5.1: Standard pricing. OpenAI official pricing (developers.openai.com/api/docs/pricing) verified 2026-11-13; standard tier; Deprecated; shutdown 2027-04-01 (replacement: gpt-6-sol)
Gemini 3.5 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-5.1 | Gemini 3.5 Flash-Lite | Ratio |
|---|---|---|---|
| Input | $1.25 | $0.30 | 4.17× |
| Output | $10.00 | $2.50 | 4.00× |
| Cached input | $0.125 | $0.03 | 4.17× |
| Cache write | — | — | — |
| Blended | $2.19 | $0.546 | 4.01× |
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.
GPT-5.1 relative to Gemini 3.5 Flash-Lite
No matching recorded settings for a cost summary.
Summary: 0 of 2 shared benchmarks have matching recorded settings and sources. The average is a geometric mean of 0 positive-cost ratios, one equal weight per benchmark. This benchmark set can include related tests and indexes; it is not a workload cost estimate.
Settings or sources differ or are not recorded; interpret the comparison with care.
GPT-5.1
Gemini 3.5 Flash-Lite
Settings or sources differ or are not recorded; interpret the comparison with care.
GPT-5.1
Gemini 3.5 Flash-Lite
| Benchmark | GPT-5.1 | Gemini 3.5 Flash-Lite |
|---|---|---|
| AA Intelligence Index v5.0.1 | Not reported | |
| AutomationBench | Not reported | $0.13 / task Average · Pass Rate: 3.4 Thinking High (With Tools) · zapier-private-heldout $0.12 / task Average · Pass Rate: 4.0 Thinking Medium (With Tools) · zapier-private-heldout |
| MedCode | Not reported | |
| MedScribe | Not reported | |
| SAGE | Not reported | |
| SWE-sweep | Not reported | |
| Tax Agent Bench | Not reported | $0.0815 / task Average · Accuracy (%, rubric × citation quality): 7.3 Thinking High (With Tools) |
| Vibe Code Bench v1.1 | Not reported |
| Attribute | GPT-5.1 | Gemini 3.5 Flash-Lite |
|---|---|---|
| Availability | Deprecated | Available |
| Provider | OpenAI | Google Deep Mind |
| Model type | Reasoning model | Multimodal model |
| First release | November 12, 2025 | July 21, 2026 |
| Context window | 400K tokens | 1M tokens |
| Max output | 128K tokens | 64K tokens |
| Architecture | Undisclosed | Undisclosed |
| Documented capabilities | Reasoning, Multilingual | Reasoning, Coding, Translation, Function calling, Tool use, Structured output, Web search, Long context |
| Input modalities | Text, Image | Text, Image, Audio, Video |
| Output modalities | Text | Text |
| Weights | Closed / API only | Closed / API only |
| Commercial use | Proprietary | 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-5.1 or Gemini 3.5 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.