Gemini 3.8 Flash vs Muse Spark 1.2
Full profiles: Gemini 3.8 Flash (Google) and Muse Spark 1.2 (Meta): every benchmark, price and rank.
Updated · Data from 10 sources
As of 24 Oct 2026, Gemini 3.8 Flash (high) and Muse Spark 1.2 (xhigh) are neck and neck on quality (64.4 vs 63.2 on the BenchLeader Index, inside the ±6.1 margin of error), and Gemini 3.8 Flash (high) costs 1.3× less, which makes it the better buy for most workloads. Gemini 3.8 Flash (high)'s current price runs until 31 Dec 2026; from 1 Jan 2027 Muse Spark 1.2 (xhigh) costs 1.5× less ($2.00 vs $3.00 per 1M blended); on use case, pick Gemini 3.8 Flash for coding (64 vs 55), Muse Spark 1.2 for maths (67 vs 62).
Gemini 3.8 Flash benchmarks high Google
Muse Spark 1.2 benchmarks xhigh MetaOpen in the comparison toolWhich 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 case | Pick | Why | Confidence |
|---|---|---|---|
| Coding | Gemini 3.8 Flash | 64 vs 55 category score; Arena WebDev 1585 vs 1534 | High |
| Agents & tool use | Muse Spark 1.2 | 55 vs 51 category score; τ³-Banking (AA) 34.9% vs 45.0% | Medium |
| Maths | Muse Spark 1.2 | 67 vs 62 category score; Arena Maths 1491 vs 1526 | Medium |
| Reasoning | Muse Spark 1.2 | 69 vs 68 category score; CritPt 17.7% vs 18.3% | Medium |
| Knowledge | Gemini 3.8 Flash | 68 vs 67 category score; SimpleQA Verified 69.7% vs 60.3% | Medium |
| Long documents | Gemini 3.8 Flash | 66 vs 65 category score; AA-LCR 81.3% vs 79.0% | Medium |
| Images and other media | Gemini 3.8 Flash | 68 vs 65 category score; Arena Vision 1315 vs 1304 | Medium |
| Chat quality (human preference) | Either | 69 vs 69 on Arena votes | Either |
| Lowest cost | Gemini 3.8 Flash (until 31 Dec 2026) | $1.50 vs $2.00 per 1M blended; agentic coding session $0.060 vs $0.092; from 1 Jan 2027: $3.00 vs $2.00 | – |
| Fastest first answer | Muse Spark 1.2 | 17.6 s (Muse Spark 1.2 (xhigh)) vs 25.1 s (Gemini 3.8 Flash (high)) to the first answer token | – |
| High volume on a budget | Neither flagship | A smaller model is usually the better fit: Cheapest good LLMs, Fastest LLMs | – |
Key differences
- Gemini 3.8 Flash (high) and Muse Spark 1.2 (xhigh) are neck and neck on quality (64.4 vs 63.2, within the ±6.1 margin).
- Gemini 3.8 Flash (high) is stronger in coding, composite, human preference, knowledge, long context, multimodal.
- Muse Spark 1.2 (xhigh) is stronger in agents & tools, 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.
- Muse Spark 1.2 (xhigh) streams 2.2× faster (307 vs 141 tokens per second).
At a glance
| Spec | Gemini 3.8 Flash | Muse Spark 1.2 |
|---|---|---|
| Developer | Meta | |
| Released | 2 Sept 2026 | 5 Aug 2026 |
| Context window (tokens) | 1,048,576 | 1,048,576 |
| Compared at | Gemini 3.8 Flash (high) | Muse Spark 1.2 (xhigh) |
| Open weights | No | No |
| Price in / out / cached input per 1M | $0.750 / $3.75 / $0.075 | $1.25 / $4.25 / $0.150 |
| Announced price change | $1.50 / $7.50 from 1 Jan 2027 | None 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.
| Category | Gemini 3.8 Flash (high) | Muse Spark 1.2 (xhigh) | Leader |
|---|---|---|---|
| Reasoning | 68.2 | 69.3 | Muse Spark 1.2 |
| Coding | 63.5 | 55.2 | Gemini 3.8 Flash |
| Agents & tools | 50.9 | 55.0 | Muse Spark 1.2 |
| Maths | 62.4 | 67.3 | Muse Spark 1.2 |
| Knowledge | 68.4 | 66.7 | Gemini 3.8 Flash |
| Human preference | 69.1 | 68.6 | level |
| Multimodal | 67.7 | 65.2 | Gemini 3.8 Flash |
| Long context | 65.7 | 64.5 | Gemini 3.8 Flash |
| Composite | 75.3 | 73.8 | Gemini 3.8 Flash |
Where sources disagree
Across the 63 benchmarks both have, Gemini 3.8 Flash leads 41, Muse Spark 1.2 leads 22. Every overall index that rates both puts Gemini 3.8 Flash ahead.
| Overall index | Gemini 3.8 Flash (high) | Muse Spark 1.2 (xhigh) | Leader |
|---|---|---|---|
| BenchLeader Index | 64.4 | 63.2 | neck and neck |
| AA Intelligence Index v4.3.2 | 40.9 | 39.6 | Gemini 3.8 Flash |
| Arena Text | 1496 | 1491 | Gemini 3.8 Flash |
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; suite cost is what Artificial Analysis paid to run its whole Intelligence Index.
| Measure | Gemini 3.8 Flash (high) | Muse Spark 1.2 (xhigh) |
|---|---|---|
| Blended price per 1M tokens, until 31 Dec 2026 | $1.50 | $2.00 |
| Input / output per 1M | $0.750 / $3.75 | $1.25 / $4.25 |
| Blended price per 1M from 1 Jan 2027 | $3.00 | $2.00 |
| Input / output per 1M from 1 Jan 2027 | $1.50 / $7.50 | $1.25 / $4.25 |
| Cached input per 1M | $0.075 | $0.150 |
| Price per task: chat reply | $0.0014 | $0.0018 |
| Price per task: summarize a 30-page report | $0.011 | $0.018 |
| Price per task: code edit | $0.010 | $0.014 |
| Price per task: agentic coding session | $0.060 | $0.092 |
| Price per task: structured extraction | $0.0023 | $0.0034 |
| Cost to run a full benchmark suite | $1.24 | $0.975 |
| Output speed | 141 tok/s | 307 tok/s |
| Time to first answer | 25.1 s | 17.6 s |
| Time to a complete answer | 28.7 s | 19.2 s |
Per token is not per task: on Artificial Analysis' full suite Gemini 3.8 Flash (high) cost $1.24 and Muse Spark 1.2 (xhigh) $0.975, because Gemini 3.8 Flash (high) used about 1.7× as many 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 64.4 and takes 25 s to its first answer token; Gemini 3.8 Flash (medium) scores 64.4 in 3 s, Gemini 3.8 Flash (low) scores 61.0 in 3 s. Muse Spark 1.2 (xhigh) scores 63.2 and takes 18 s to its first answer token. 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
139 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.
| Metric | Publisher | Gemini 3.8 Flash (high) | Muse Spark 1.2 (xhigh) |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 64.4 | 63.2 |
| Agents & tools score | BenchLeader | 50.9 | 55.0 |
| Coding score | BenchLeader | 63.5 | 55.2 |
| Composite score | BenchLeader | 75.3 | 73.8 |
| Human preference score | BenchLeader | 69.1 | 68.6 |
| Knowledge score | BenchLeader | 68.4 | 66.7 |
| Long context score | BenchLeader | 65.7 | 64.5 |
| Maths score | BenchLeader | 62.4 | 67.3 |
| Multimodal score | BenchLeader | 67.7 | 65.2 |
| Reasoning score | BenchLeader | 68.2 | 69.3 |
| Blended price $/M | BenchLeader | $1.50 | $2.00 |
| Output speed | BenchLeader | 141 tok/s | 307 tok/s |
| Time to first answer | BenchLeader | 25.1 s | 17.6 s |
| Context window | BenchLeader | 1,048,576 tokens | 1,048,576 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 95.4% | – |
| Humanity's Last Exam | Scale AI / CAIS | 44.5%† | – |
| SimpleBench | SimpleBench | – | 74.5%† |
| Arena Hard Prompts | Arena (LMArena) | 1517 | 1512 |
| LiveBench 2.0 Reasoning | LiveBench | 89.3%† | 90.0%† |
| LiveBench 1.0 Reasoning | LiveBench | 89.3% | 90.0% |
| GPQA Diamond (AA) | Artificial Analysis | 95.3% | 90.4% |
| Humanity's Last Exam (AA) | Artificial Analysis | 47.8% | 45.5% |
| GPQA Diamond (Vals) | Vals AI | 94.4% | – |
| ARC-AGI-1 | ARC Prize | 98.5% | – |
| ARC-AGI-2 | ARC Prize | 89.2% | – |
| ARC-AGI-3 | ARC Prize | 35.0% | – |
| CritPt | Artificial Analysis | 18.3% | 17.7% |
| MysteryMechanism | Vals AI | 36.5% | – |
| Chess Puzzles | Epoch AI Benchmarking Hub | 58.0% | 27.0% |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 47.0% | – |
| LMCA | Epoch AI Benchmarking Hub | 51.5%† | 48.4% |
| DTBench | Epoch AI Benchmarking Hub | 95.7%† | 94.7% |
| Coding | |||
| SciCode | SciCode | 56.6% | 57.4% |
| WeirdML | WeirdML | 84.8% | 60.3% |
| FrontierCode | Cognition | 41.2%† | – |
| Arena Coding | Arena (LMArena) | 1528 | 1541 |
| Arena WebDev | Arena (LMArena) | 1585 | 1534 |
| LiveBench 2.0 Coding | LiveBench | 82.2%† | 78.2%† |
| LiveBench 1.0 Coding | LiveBench | 72.5% | 77.5% |
Show all 139 benchmarks
| Metric | Publisher | Gemini 3.8 Flash (high) | Muse Spark 1.2 (xhigh) |
|---|---|---|---|
| Coding | |||
| LiveCodeBench | Vals AI | 89.5% | – |
| IOI | Vals AI | 56.9% | 21.8% |
| SWE-bench (Vals) | Vals AI | 80.0% | 86.6% |
| Code Migration | Vals AI | 36.5% | 29.9% |
| Code Migration v1.1 | Vals AI | 38.6% | – |
| ProgramBench | Vals AI | 1.0% | 0.5% |
| SWE-bench Multimodal | Vals AI | 40.8% | – |
| Vibe Code Bench 1-100 | Vals AI | 18.8% | – |
| Vibe Code Bench v1.1 | Vals AI | 78.7% | 79.1% |
| SWE Atlas: Codebase QnA | Scale AI SEAL | 47.0%† | – |
| SWE Atlas: Refactoring | Scale AI SEAL | 44.8%† | – |
| SWE Atlas: Test Writing | Scale AI SEAL | 53.7%† | – |
| Surface Evolver Bench | Epoch AI Benchmarking Hub | 76.9% | – |
| DeepSWE v1.1 | Epoch AI Benchmarking Hub | 73.8% | 54.9% |
| CursorBench | Cursor | 39.6% | – |
| ALE-Bench | Epoch AI Benchmarking Hub | 1269.7 | – |
| FrontierSWE | Epoch AI Benchmarking Hub | 19.6% | 12.0% |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 19.7% | 7.1% |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | 87.6% | 80.2% |
| Startrise Frontend | Startrise | 64.6%† | 70.3%† |
| FrontierCode 1.1 (AA) | Artificial Analysis | 36.4% | – |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | 19.1% | – |
| Remote Labor Index | Scale AI / CAIS | 5.8%† | – |
| APEX-Agents | Mercor | 64.3%† | 45.4%† |
| Arena Agent | Arena (LMArena) | 3.6 | -6.8 |
| LiveBench Long Agentic | LiveBench | 30.1%† | 21.3%† |
| LiveBench Browser | LiveBench | 64.0%† | 36.0%† |
| LiveBench Agentic Coding | LiveBench | 54.2% | 57.6% |
| Terminal-Bench 2.1 (Vals) | Vals AI | 81.3% | 69.7% |
| HiL-Bench | Scale AI SEAL | 41.5%† | – |
| GDPval-AA v2.1 | Artificial Analysis | 46.8% | – |
| τ³-Banking (AA) | Artificial Analysis | 45.0% | 34.9% |
| ITBench SRE (AA) | Artificial Analysis | 52.5% | – |
| Analyst Agent (AA) | Artificial Analysis | 46.3% | – |
| CUA-bench | Vals AI | 4.2% | – |
| CyberBench | Vals AI | 43.8% | 69.5% |
| Finance Agent v2 | Vals AI | 61.4% | 60.6% |
| Finance Agent v2.1 | Vals AI | 65.8% | – |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | 12.1% | – |
| Harvey's Legal Agent Benchmark v1 | Vals AI | 10.0% | 25.4% |
| Legal Research Bench | Vals AI | 38.9% | 43.8% |
| SkillsBench | Vals AI | 58.0% | 53.0% |
| SREBench | Vals AI | 11.1% | 0.0% |
| Tax Agent Bench | Vals AI | 32.1% | 32.8% |
| Terminal-Bench 4.0 (Vals) | Vals AI | 19.7% | 6.1% |
| Terminal-Bench Science | Vals AI | 8.6% | – |
| Time Horizon Index: KSP | Vals AI | 18.8% | – |
| Vending-Bench 2 | Andon Labs | 5093.8† | – |
| AutomationBench | Artificial Analysis | 59.9% | 40.6% |
| GDP.pdf (AA) | Artificial Analysis | 21.0% | 17.4% |
| Harvey LAB-AA v1.1 | Harvey | 0.0% | – |
| EnterpriseOps-Gym | Artificial Analysis | – | 47.3% |
| AA-Briefcase v1.1 | Artificial Analysis | 1202 | – |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 10.0% | – |
| CWE-Bench (AA) | Artificial Analysis | 52.5% | – |
| DeepSec-Bench (AA) | Artificial Analysis | 14.5% | – |
| CyberGym end-to-end (AA) | Artificial Analysis | 8.4% | – |
| FACTS Search | 76.3%† | – | |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 68.4% | – |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 21.9% | – |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 98.9% | – |
| ProofBench | Vals AI | 48.0%† | 43.0%† |
| LiveBench Mathematics | LiveBench | 91.6% | 91.2% |
| Arena Maths | Arena (LMArena) | 1526 | 1491 |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 69.7% | 60.3% |
| LiveBench 2.0 Data Analysis | LiveBench | 54.0%† | 76.5%† |
| LiveBench Research | LiveBench | 79.1%† | 67.7%† |
| LiveBench 1.0 Data Analysis | LiveBench | 54.0% | 76.5% |
| AA-Omniscience | Artificial Analysis | 29.6 | 27.2 |
| MMLU-Pro | Vals AI | 90.2% | 88.3% |
| LegalBench | Vals AI | 87.0% | 85.3% |
| CorpFin | Vals AI | – | 70.9% |
| TaxEval | Vals AI | 74.5% | 80.4% |
| PRBench Finance | Scale AI SEAL | 49.5%† | – |
| PRBench Legal | Scale AI SEAL | 48.9%† | – |
| BioMysteryBench | Vals AI | 62.2% | 64.8% |
| Excel Modeling Benchmark | Vals AI | 72.2% | 57.0% |
| Excel Modeling Benchmark v1.1 | Vals AI | 72.9% | – |
| MedCode | Vals AI | 48.1% | 49.4% |
| MedScribe | Vals AI | 84.5% | 90.1% |
| Public Benefits Bench v1.1 | Vals AI | 65.3% | 68.5% |
| GDP.pdf | Epoch AI Benchmarking Hub | 23.2% | 16.0% |
| AA-Omniscience: accuracy | Artificial Analysis | 54.6% | 45.4% |
| AA-Omniscience: non-hallucination | Artificial Analysis | 44.8% | 66.7% |
| Instruction following | |||
| LiveBench Language | LiveBench | 87.8% | 78.6% |
| LiveBench Instruction Following | LiveBench | 81.4% | 74.3% |
| Arena Instruction Following | Arena (LMArena) | 1490 | 1472 |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1496 | 1491 |
| Arena Creative Writing | Arena (LMArena) | 1485 | 1439 |
| Arena Multi-turn | Arena (LMArena) | 1504 | 1511 |
| Arena Longer Queries | Arena (LMArena) | 1510 | 1488 |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | 1315 | 1304 |
| LiveBench Design | LiveBench | 72.7%† | 67.1%† |
| MMMU-Pro | Artificial Analysis | 85.6% | – |
| MMMU-Pro (Vals) | Vals AI | 89.1% | 86.1% |
| MortgageTax | Vals AI | 65.3% | 65.4% |
| SAGE | Vals AI | 35.1% | 47.7% |
| AudioMC | Scale AI SEAL | 60.4% | – |
| AudioMC (text output) | Scale AI SEAL | 60.4% | – |
| Blueprint-Bench 2 | Epoch AI Benchmarking Hub | 38.6%† | – |
| AA-3D | Artificial Analysis | 969 | – |
| Long context | |||
| AA-LCR | Artificial Analysis | 81.3% | 79.0% |
| MLCR | Artificial Analysis | 10.6% | 7.2% |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 157.4† | 155.1† |
| LiveBench 2.0 | LiveBench | 67.3%† | 62.4%† |
| LiveBench 1.0 | LiveBench | 75.8% | 78.0% |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 40.9 | 39.6 |
| Vals Index | Vals AI | 56.0 | – |
| Vals Finance Index | Vals AI | 60.5% | – |
| Vals RSI Index | Vals AI | 19.9% | – |
| Vals Science Index | Vals AI | 35.8% | – |
| Vals Multimodal Index | Vals AI | – | 69.8%† |
| Vals Router Index | Vals AI | 56.0%† | – |
| AA Cyber Index | Artificial Analysis | 25.1 | – |
Data as of 2026-10-24. Best configuration of each model; every score links to its source on the model pages.
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): 8 new results (Code Migration v1.1, Excel Modeling Benchmark v1.1, Finance Agent v2.1…).
- Muse Spark 1.2 (xhigh): 1 new result (Harvey's Legal Agent Benchmark v1).
- Gemini 3.8 Flash (high): 1 score revision.
- Muse Spark 1.2 (xhigh): 2 score revisions.
- Gemini 3.8 Flash (high): 3 score revisions.
- Gemini 3.8 Flash (high): BenchLeader Index 63.7 → 64.5.
- Muse Spark 1.2 (xhigh): BenchLeader Index 62.6 → 63.3.
- Muse Spark 1.2 (xhigh): 4 new results (AutomationBench, GDP.pdf (AA), MLCR…).
- Gemini 3.8 Flash (high): 1 new result (AudioMC (text output)).
Related comparisons
- Gemini 3.8 Flash vs Claude Opus 5.5
- Gemini 3.8 Flash vs Gemini 4 Argon
- Gemini 3.8 Flash vs Muse Wonder Full
- Muse Spark 1.2 vs Claude Opus 5.5
- Muse Spark 1.2 vs Gemini 4 Argon
- Muse Spark 1.2 vs Muse Wonder Full
- Muse Spark 1.2 vs Claude Fable 5.1
- Gemini 3.7 Flash vs Muse Spark 1.2
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
Gemini 3.8 Flash vs Muse Spark 1.2: questions
- Is Gemini 3.8 Flash better than Muse Spark 1.2?
- Gemini 3.8 Flash (high) and Muse Spark 1.2 (xhigh) are neck and neck on quality (64.4 vs 63.2, within the ±6.1 margin). The BenchLeader Index combines every independent quality benchmark; the two are within the margin of error as of 2026-10-24, so check the category scores for your use.
- Which is cheaper, Gemini 3.8 Flash or Muse Spark 1.2, 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. Yes, that changes: Gemini 3.8 Flash's list price changes on 1 Jan 2027, and from then Muse Spark 1.2 is cheaper ($2.00 vs $3.00 blended).
- Is Gemini 3.8 Flash better than Muse Spark 1.2 for coding?
- Gemini 3.8 Flash scores higher in coding (64 vs 55 on the category index, where 50 is average). On Arena WebDev, the top shared coding benchmark, it is 1585 for Gemini 3.8 Flash against 1534 for Muse Spark 1.2.
- Is Gemini 3.8 Flash better than Muse Spark 1.2 for agents and tool use?
- Muse Spark 1.2 scores higher in agentic tasks (55 vs 51 on the category index, where 50 is average). On τ³-Banking (AA), the top shared agents & tools benchmark, it is 45.0% for Gemini 3.8 Flash against 34.9% for Muse Spark 1.2.
- Which is better for long documents?
- Gemini 3.8 Flash scores higher on long-context benchmarks (66 vs 65). Both accept 1,048,576 tokens of context.
- Which has lower latency?
- Muse Spark 1.2 (xhigh) answers first: 17.6 s against 25.1 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.
- Which is faster, Gemini 3.8 Flash or Muse Spark 1.2?
- Muse Spark 1.2 streams faster: 307 against 141 output tokens per second.
- Do independent benchmarks agree on Gemini 3.8 Flash vs Muse Spark 1.2?
- Across the 63 benchmarks both have, Gemini 3.8 Flash leads 41, Muse Spark 1.2 leads 22. Every overall index that rates both puts Gemini 3.8 Flash ahead.
- When was Gemini 3.8 Flash released?
- Gemini 3.8 Flash was released on 2 Sept 2026.