BenchLeader

Gemini 3.8 Flash vs GPT-6.1 Terra

Full profiles: Gemini 3.8 Flash (Google) and GPT-6.1 Terra (OpenAI): every benchmark, price and rank.

Updated · Data from 13 sources

As of 10 Nov 2026, GPT-6.1 Terra is ahead of Gemini 3.8 Flash on quality (64.9 vs 61.8 on the BenchLeader Index), but Gemini 3.8 Flash is 1.3× cheaper at $1.50 vs $2.00 per 1M tokens blended. Choose Gemini 3.8 Flash for knowledge (64 vs 62) and fast first answers (16.6 s vs 147.0 s), where it also streams ~1.5× faster; choose GPT-6.1 Terra for agents & tools (69 vs 51), maths (72 vs 62), and coding (70 vs 60). Gemini 3.8 Flash's current price runs until 31 Dec 2026, then $3.00.

Key facts (as of 10 Nov 2026)

  • Gemini 3.8 Flash scores 61.8 on the BenchLeader Index and GPT-6.1 Terra scores 64.9 (BenchLeader, 10 Nov 2026).
  • Gemini 3.8 Flash costs $1.50 per 1M tokens blended until 31 Dec 2026, then $3.00 (https://ai.google.dev/gemini-api/docs/pricing, checked 20 Oct 2026).
  • GPT-6.1 Terra costs $2.00 per 1M tokens blended (list price, 10 Nov 2026).
  • Gemini 3.8 Flash streams ~1.5× faster than GPT-6.1 Terra (Artificial Analysis, 7-day median, 10 Nov 2026).
  • Of the 37 benchmarks both models have, GPT-6.1 Terra leads 25 (BenchLeader, 10 Nov 2026).
  • On Arena WebDev, Gemini 3.8 Flash is rated 1584 and GPT-6.1 Terra 1679 (LMArena, as published by 10 Nov 2026).

Which to pick for…

The pick's numbers come first. Category scores on the BenchLeader scale (50 is the average model, 15 points one standard deviation). High confidence means a lead of half a standard deviation or more; under one point is called either.

Use casePickWhyConfidence
CodingGPT-6.1 Terra70 vs 60 category score; Arena WebDev 1679 vs 1584High
Agents & tool useGPT-6.1 Terra69 vs 51 category score; Arena Agent 12.1 vs 2.4High
MathsGPT-6.1 Terra72 vs 62 category score; FrontierMath Tiers 1–3 90.9% vs 68.4%High
ReasoningGPT-6.1 Terra69 vs 63 category score; HLE-Diamond (AA) 47.3% vs 33.1%Medium
KnowledgeGemini 3.8 Flash64 vs 62 category score; SimpleQA Verified 69.7% vs 57.3%Medium
Long documentsEither65 vs 66 category score; AA-LCR v1.1 81.3% vs 82.7%Either
Images and other mediaEither68 vs 67 category score; MMMU-Pro 85.6% vs 84.7%Either
Chat quality (human preference)–Only Gemini 3.8 Flash has an Arena rating (69 category score)Not comparable
Lowest costGemini 3.8 Flash (until 31 Dec 2026)$1.50 vs $2.00 per 1M blended; agentic coding session $0.060 vs $0.080; from 1 Jan 2027: $3.00 vs $2.00–
Fastest first answerGemini 3.8 Flash16.6 s (Gemini 3.8 Flash (high)) vs 147.0 s (GPT-6.1 Terra (max)) to the first answer token–
High volume on a budgetNeither flagshipA smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs–

Key differences

  • GPT-6.1 Terra (max) leads on quality: 64.9 vs 61.8.
  • Gemini 3.8 Flash (high) is stronger in human preference, knowledge, multimodal.
  • GPT-6.1 Terra (max) is stronger in agents & tools, coding, long context, maths, reasoning.
  • Gemini 3.8 Flash (high) is 1.3× cheaper ($1.50 vs $2.00 per 1M blended) until 31 Dec 2026, then $3.00 vs $2.00 from 1 Jan 2027.
  • Gemini 3.8 Flash (high) streams 1.5× faster (112 vs 73 tokens per second).

At a glance

SpecGemini 3.8 FlashGPT-6.1 Terra
DeveloperGoogleOpenAI
Released2 Sep 202626 Oct 2026
Context window (tokens)1,048,5761,050,000
Compared atGemini 3.8 Flash (high)GPT-6.1 Terra (max)
Open weightsNoNo
Price in / out / cached input per 1M$0.750 / $3.75 / $0.075$1.00 / $5.00 / $0.050
Announced price change$1.50 / $7.50 from 1 Jan 2027None announced

Limits, availability and announced prices from the vendors' own pages: ai.google.dev pricing (checked 20 Oct 2026). Everything else is from the day's data.

Category by category

Category scores on the BenchLeader scale: 50 is the average evaluated model, 15 points is one standard deviation. A gap under one point is called level.

CategoryGemini 3.8 Flash (high)GPT-6.1 Terra (max)Leader
Reasoning63.268.6GPT-6.1 Terra
Coding60.269.8GPT-6.1 Terra
Agents & tools51.069.1GPT-6.1 Terra
Maths61.872.1GPT-6.1 Terra
Knowledge64.161.9Gemini 3.8 Flash
Human preference69.2–not comparable
Multimodal67.567.2level
Long context65.466.1level

On one chart

Each domain on the index's own scale, where 50 is an average model. Click a domain to see the benchmarks behind it. Pick up to 5 models from the list.

2550 avg75ReasoningCodingAgents & toolsMathsKnowledgeLong contextMultimodalGemini 3.8 Flash, Reasoning: 63.2Gemini 3.8 Flash, Coding: 60.2Gemini 3.8 Flash, Agents & tools: 51.0Gemini 3.8 Flash, Maths: 61.8Gemini 3.8 Flash, Knowledge: 64.1Gemini 3.8 Flash, Long context: 65.4Gemini 3.8 Flash, Multimodal: 67.5GPT-6.1 Terra, Reasoning: 68.6GPT-6.1 Terra, Coding: 69.8GPT-6.1 Terra, Agents & tools: 69.1GPT-6.1 Terra, Maths: 72.1GPT-6.1 Terra, Knowledge: 61.9GPT-6.1 Terra, Long context: 66.1GPT-6.1 Terra, Multimodal: 67.2

Not drawn, measured for fewer than two of these models: Instruction following, Human preference.

ModelIndex

Where sources disagree

Across the 37 benchmarks both have, Gemini 3.8 Flash leads 12, GPT-6.1 Terra leads 25. Every overall index that rates both puts GPT-6.1 Terra ahead.

Overall indexGemini 3.8 Flash (high)GPT-6.1 Terra (max)Leader
BenchLeader Index61.864.9GPT-6.1 Terra
AA Intelligence Index v5.030.951.3GPT-6.1 Terra
Vals Index56.060.5GPT-6.1 Terra

Each publisher runs its own tasks, harnesses and effort settings, so their overall verdicts can differ; BenchLeader reconciles them on one scale. † measured at another effort setting of the same model (the publisher did not test the one compared here).

Price, speed and latency

List prices blended at three input tokens per output token. Per-task prices use the token counts on the methodology page. Cost, tokens and time per benchmark task are measured: Artificial Analysis’ averages over its whole Intelligence Index run.

MeasureGemini 3.8 Flash (high)GPT-6.1 Terra (max)
Blended price per 1M tokens, until 31 Dec 2026$1.50$2.00
Input / output per 1M$0.750 / $3.75$1.00 / $5.00
Blended price per 1M from 1 Jan 2027$3.00$2.00
Input / output per 1M from 1 Jan 2027$1.50 / $7.50$1.00 / $5.00
Cached input per 1M$0.075$0.050
Price per task: chat reply$0.0014$0.0019
Price per task: summarize a 30-page report$0.011$0.015
Price per task: code edit$0.010$0.013
Price per task: agentic coding session$0.060$0.080
Price per task: structured extraction$0.0023$0.0030
Agentic coding session, input mostly cached$0.030$0.037
Cost per benchmark task (AA Index)$7.77$0.961
Output tokens per task (AA Index)99k60k
Of which reasoning60k39k
Time per task (AA Index)15 min14 min
Output speed112 tok/s73 tok/s
Time to first answer16.6 s147.0 s
Time to a complete answer50.3 s316.8 s

Per token is not per task: an average task of Artificial Analysis' Intelligence Index cost $7.77 on Gemini 3.8 Flash (high) and $0.961 on GPT-6.1 Terra (max), and Gemini 3.8 Flash (high) wrote 1.7× as many output tokens for the same work, which a per-token price hides.

Each model is compared at its best-ranked reasoning-effort setting. Gemini 3.8 Flash (high) scores 61.8 and takes 17 s to its first answer token; Gemini 3.8 Flash (medium) scores 60.3 in 11 s, Gemini 3.8 Flash (low) scores 56.0 in 4 s. GPT-6.1 Terra (max) scores 64.9 and takes 147 s to its first answer token; GPT-6.1 Terra (xhigh) scores 60.2 in 27 s, GPT-6.1 Terra (high) scores 59.7 in 10 s. Higher effort means more thinking before the answer: better scores, longer waits and more tokens billed. How reasoning effort changes scores and cost.

Every benchmark

152 benchmarks, grouped by category; each name links to the board and its leaders. † measured at another effort setting of the same model, shown for reference and not counted as a win.

MetricPublisherGemini 3.8 Flash (high)GPT-6.1 Terra (max)
BenchLeader IndexBenchLeader61.864.9
Agents & tools scoreBenchLeader51.069.1
Coding scoreBenchLeader60.269.8
Human preference scoreBenchLeader69.2–
Knowledge scoreBenchLeader64.161.9
Long context scoreBenchLeader65.466.1
Maths scoreBenchLeader61.872.1
Multimodal scoreBenchLeader67.567.2
Reasoning scoreBenchLeader63.268.6
Blended price $/MBenchLeader$1.50$2.00
Output speedBenchLeader112 tok/s73 tok/s
Time to first answerBenchLeader16.6 s147.0 s
Context windowBenchLeader1,048,576 tokens1,050,000 tokens
Reasoning
GPQA DiamondEpoch AI Benchmarking Hub95.4%94.3%
Humanity's Last ExamScale AI / CAIS44.5%†–
Arena Hard PromptsArena (LMArena)1520–
LiveBench 2.0 ReasoningLiveBench89.3%†88.7%†
LiveBench 1.0 ReasoningLiveBench89.3%–
GPQA Diamond (AA)Artificial Analysis95.3%–
Humanity's Last Exam (AA)Artificial Analysis47.8%46.3%
HLE-Diamond (AA)Artificial Analysis33.1%47.3%
GPQA Diamond (Vals)Vals AI94.4%–
ARC-AGI-1ARC Prize98.5%–
ARC-AGI-2ARC Prize89.2%–
ARC-AGI-3ARC Prize35.0%–
CritPtArtificial Analysis18.3%28.0%
CritPt v2 hard subset (AA)Artificial Analysis46.5%68.0%
MysteryMechanismVals AI36.5%–
Chess PuzzlesEpoch AI Benchmarking Hub58.0%–
Mystery Game PuzzlesEpoch AI Benchmarking Hub47.0%74.0%
LMCAEpoch AI Benchmarking Hub51.5%†–
DTBenchEpoch AI Benchmarking Hub95.7%†–
Coding
SciCodeSciCode56.6%55.1%
WeirdMLWeirdML84.8%–
FrontierCodeCognition41.2%†–
Arena CodingArena (LMArena)1531–
Arena WebDevArena (LMArena)15841679
LiveBench 2.0 CodingLiveBench65.7%†89.2%†
Show all 152 benchmarks
MetricPublisherGemini 3.8 Flash (high)GPT-6.1 Terra (max)
Coding
LiveBench 1.0 CodingLiveBench72.5%–
LiveCodeBenchVals AI89.5%–
IOIVals AI56.9%–
SWE-bench (Vals)Vals AI80.0%–
Code MigrationVals AI36.5%–
Code Migration v1.1Vals AI38.6%–
ProgramBenchVals AI1.0%–
SWE-bench MultimodalVals AI40.8%–
Vibe Code Bench 1-100Vals AI18.8%–
Vibe Code Bench v1.1Vals AI78.7%84.0%
SWE Atlas: Codebase QnAScale AI SEAL47.0%†–
SWE Atlas: RefactoringScale AI SEAL44.8%†–
SWE Atlas: Test WritingScale AI SEAL53.7%†–
Surface Evolver BenchEpoch AI Benchmarking Hub76.9%–
DeepSWE v1.1Epoch AI Benchmarking Hub73.8%–
CursorBenchCursor39.6%–
ALE-BenchEpoch AI Benchmarking Hub1269.72608.8
FrontierSWEEpoch AI Benchmarking Hub19.6%–
Terminal-Bench 4.0 (AA)Artificial Analysis19.7%55.6%
Terminal-Bench 2.1 (AA)Artificial Analysis87.6%–
Startrise FrontendStartrise64.6%†82.0%†
GameBench 2 OverallDuelLab GameBench 259.0†–
GameBench 2 by reasoning settingDuelLab GameBench 264.2–
Design Arena WebsiteDesign Arena1296†1288†
FrontierCode 1.1 (AA)Artificial Analysis36.4%36.0%
FrontierCode 2.0 (AA)Artificial Analysis18.7%42.3%
Agents & tools
Terminal-BenchTerminal-Bench18.2%–
Remote Labor IndexScale AI / CAIS5.8%†–
APEX-AgentsMercor64.3%†68.3%
Arena AgentArena (LMArena)2.412.1
LiveBench Long AgenticLiveBench16.5%†56.2%†
LiveBench BrowserLiveBench45.1%†93.1%†
LiveBench Agentic CodingLiveBench54.2%–
Terminal-Bench 2.1 (Vals)Vals AI81.3%–
HiL-BenchScale AI SEAL41.5%†68.0%†
GDPval-AA v2.1, normalised scoreArtificial Analysis46.8%–
GDPval-AA v2.1Artificial Analysis14451476
τ³-Banking (AA)Artificial Analysis45.0%–
ITBench SRE (AA)Artificial Analysis52.5%–
Analyst Agent (AA)Artificial Analysis46.3%–
CUA-benchVals AI4.2%–
CyberBenchVals AI43.8%–
Finance Agent v2Vals AI61.4%–
Finance Agent v2.1Vals AI65.8%56.0%
Harvey's Legal Agent Benchmark v1.1Vals AI12.1%1.7%
Harvey's Legal Agent Benchmark v1Vals AI10.0%–
Legal Research BenchVals AI38.9%26.0%
SkillsBenchVals AI58.0%–
SREBenchVals AI11.1%–
Tax Agent BenchVals AI32.1%17.1%
Terminal-Bench 4.0 (Vals)Vals AI19.7%49.5%
Terminal-Bench ScienceVals AI8.6%–
Time Horizon Index: KSPVals AI18.8%–
Vending-Bench 2Andon Labs5093.8†9107.5†
AutomationBenchArtificial Analysis59.9%60.2%
GDP.pdf (AA)Artificial Analysis21.0%28.6%
Harvey LAB-AA v1.1Harvey0.0%–
AA-Briefcase v1.1Artificial Analysis12031403
GDPxGDPx by SemiAnalysis–8.5%
Design Arena AgenticDesign Arena1217†1189†
Terminal-Bench-Science 0.1 (AA)Artificial Analysis10.0%57.6%
CWE-Bench (AA)Artificial Analysis52.5%–
DeepSec-Bench (AA)Artificial Analysis14.5%–
CyberGym end-to-end (AA)Artificial Analysis8.4%–
FACTS SearchGoogle80.4%†–
Maths
FrontierMath Tiers 1–3Epoch AI Benchmarking Hub68.4%90.9%
FrontierMath Tier 4Epoch AI Benchmarking Hub21.9%92.7%
OTIS Mock AIMEEpoch AI Benchmarking Hub98.9%100.0%
ProofBenchVals AI48.0%†–
LiveBench MathematicsLiveBench91.6%–
Arena MathsArena (LMArena)1520–
Knowledge
SimpleQA VerifiedEpoch AI Benchmarking Hub69.7%57.3%
LiveBench 2.0 Data AnalysisLiveBench54.0%†82.3%†
LiveBench ResearchLiveBench79.4%†79.1%†
LiveBench 1.0 Data AnalysisLiveBench54.0%–
AA-Omniscience v1.1Artificial Analysis23.329.6
MMLU-ProVals AI90.2%–
LegalBenchVals AI87.0%–
TaxEvalVals AI74.5%–
PRBench FinanceScale AI SEAL49.5%†–
PRBench LegalScale AI SEAL48.9%†–
BioMysteryBenchVals AI62.2%–
Excel Modeling BenchmarkVals AI72.2%–
Excel Modeling Benchmark v1.1Vals AI72.9%73.3%
MedCodeVals AI48.1%–
MedScribeVals AI84.5%–
Public Benefits Bench v1.1Vals AI65.3%–
EBR-benchEpoch AI Benchmarking Hub–78.1%
GDP.pdfEpoch AI Benchmarking Hub23.2%–
AA-Omniscience v1.1: accuracyArtificial Analysis50.5%47.6%
AA-Omniscience v1.1: non-hallucinationArtificial Analysis44.9%65.5%
HealthBench Professional (AA)OpenAI51.7%–
Instruction following
LiveBench LanguageLiveBench87.8%–
LiveBench Instruction FollowingLiveBench81.4%–
MultiChallengeScale AI SEAL–74.2%†
Arena Instruction FollowingArena (LMArena)1492–
Human preference
Arena TextArena (LMArena)1498–
Arena Creative WritingArena (LMArena)1489–
Arena Multi-turnArena (LMArena)1505–
Arena Longer QueriesArena (LMArena)1511–
Multimodal
Arena VisionArena (LMArena)1317–
LiveBench DesignLiveBench69.7%†79.7%†
MMMU-ProArtificial Analysis85.6%84.7%
MMMU-Pro (Vals)Vals AI89.1%–
MortgageTaxVals AI65.3%–
SAGEVals AI88.2%–
AudioMCScale AI SEAL60.4%–
AudioMC (text output)Scale AI SEAL60.4%–
Blueprint-Bench 2Epoch AI Benchmarking Hub38.6%†42.1%†
Code2Video-AAArtificial Analysis899–
AA-3DArtificial Analysis974–
Long context
AA-LCR v1.1Artificial Analysis81.3%82.7%
Arena DocumentArena (LMArena)1469–
MLCRArtificial Analysis10.6%30.6%
Composite
Epoch Capabilities IndexEpoch AI Benchmarking Hub158.7†168.1†
LiveBench 2.0LiveBench56.0%†78.8%†
LiveBench 1.0LiveBench75.8%–
AA Intelligence Index v5.0Artificial Analysis30.951.3
AA Intelligence Index v4.3.2Artificial Analysis40.948.1
AA Progress Index v1Artificial Analysis320.3345.2
Vals IndexVals AI56.060.5
Vals Finance IndexVals AI60.5%53.3%
Vals RSI IndexVals AI19.9%–
Vals Science IndexVals AI35.8%–
Vals Router IndexVals AI56.0%†–
AA Cyber IndexArtificial Analysis25.1–
Safety & honesty
FORTRESSScale AI SEAL–18.2%†

Data as of 2026-11-10. Best configuration of each model; every score links to its source on the model pages.

DuelLab GameBench 2, release gb2-20261103-eaea31df94e6 (https://benchmarks.duellab.org/releases/gb2-20261103-eaea31df94e6/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.

What changed

  • Gemini 3.8 Flash: list price moves to $1.50 / $7.50 per 1M input / output tokens (announced).
  • Gemini 3.8 Flash (high): 2 score revisions.
  • GPT-6.1 Terra (max): 1 score revision.
  • Gemini 3.8 Flash (high): 1 new result (Arena Document); 1 score revision.
  • GPT-6.1 Terra (max): 1 score revision.
  • GPT-6.1 Terra (max): 1 score revision.
  • Gemini 3.8 Flash (high): 2 score revisions.
  • GPT-6.1 Terra (max): 1 score revision.
  • GPT-6.1 Terra (max): 1 score revision.
  • GPT-6.1 Terra (max): BenchLeader Index 64.7 → 65.2.

Rankings: Best LLM overall · Best LLM for coding · Best LLM for agents · Best cheap LLMs

Gemini 3.8 Flash vs GPT-6.1 Terra: questions

Is GPT-6.1 Terra better than Gemini 3.8 Flash?
GPT-6.1 Terra (max) leads on quality: 64.9 vs 61.8. The BenchLeader Index combines every independent quality benchmark; GPT-6.1 Terra (max) is ahead overall as of 10 Nov 2026, but check the category scores for your use.
Gemini 3.8 Flash vs GPT-6.1 Terra: which is cheaper, and will that change?
Gemini 3.8 Flash is cheaper today: $1.50 against $2.00 per million tokens, blended at three input tokens per output token. Gemini 3.8 Flash's current price runs until 31 Dec 2026, then $3.00.
Is Gemini 3.8 Flash or GPT-6.1 Terra better for coding?
GPT-6.1 Terra scores higher in coding (70 vs 60 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1584 for Gemini 3.8 Flash against 1679 for GPT-6.1 Terra.
Which is faster, Gemini 3.8 Flash or GPT-6.1 Terra?
Gemini 3.8 Flash streams ~1.5× faster (112 vs 73 output tokens per second, Artificial Analysis 7-day median).
Is Gemini 3.8 Flash or GPT-6.1 Terra better for agents and tool use?
GPT-6.1 Terra scores higher in agentic tasks (69 vs 51 on the category index, where 50 is average). On Arena Agent, the top shared agents & tools benchmark, it is 2.4 for Gemini 3.8 Flash against 12.1 for GPT-6.1 Terra.
More questions (4)
Which is better for long documents?
They are level on long-context benchmarks (65 vs 66). Both take about 1.1M tokens: Gemini 3.8 Flash 1,048,576, GPT-6.1 Terra 1,050,000.
Which has lower latency?
Gemini 3.8 Flash answers first: 16.6 s against 147.0 s to the first answer token, as Artificial Analysis measures it. Reasoning effort drives most of this: a higher setting thinks longer before it answers.
Do independent benchmarks agree on Gemini 3.8 Flash vs GPT-6.1 Terra?
Across the 37 benchmarks both have, Gemini 3.8 Flash leads 12, GPT-6.1 Terra leads 25. Every overall index that rates both puts GPT-6.1 Terra ahead.
When was GPT-6.1 Terra released?
GPT-6.1 Terra was released on 26 Oct 2026.