Gemini 3.8 Flash vs Muse Spark
Full profiles: Gemini 3.8 Flash (Google) and Muse Spark (Meta): every benchmark, price and rank.
Updated · Data from 10 sources
As of 24 Oct 2026, Gemini 3.8 Flash (high) and Muse Spark are neck and neck on quality (64.4 vs 64.3, inside the ±5.0 margin of error) and close on price, so pick on the category that matters to you. Pick Gemini 3.8 Flash for knowledge (68 vs 63); pick Muse Spark for agents & tools (66 vs 51).
Gemini 3.8 Flash benchmarks 
Muse Spark benchmarks 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 case | Pick | Why | Confidence |
|---|---|---|---|
| Coding | Muse Spark | 65 vs 64 category score; Arena Coding 1529 vs 1528 | Medium |
| Agents & tool use | Muse Spark | 66 vs 51 category score | High |
| Maths | Gemini 3.8 Flash | 62 vs 59 category score; Arena Maths 1526 vs 1467 | Medium |
| Reasoning | Gemini 3.8 Flash | 68 vs 65 category score; GPQA Diamond 95.4% vs 89.8% | Medium |
| Knowledge | Gemini 3.8 Flash | 68 vs 63 category score; AA-Omniscience 29.6 vs 7.2 | Medium |
| Long documents | Gemini 3.8 Flash | 66 vs 64 category score; AA-LCR 81.3% vs 78.0% | Medium |
| Images and other media | Gemini 3.8 Flash | 68 vs 65 category score; Arena Vision 1315 vs 1306 | Medium |
| Chat quality (human preference) | Either | 69 vs 68 on Arena votes | Either |
| 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 are neck and neck on quality (64.4 vs 64.3, within the ±5.0 margin).
- Gemini 3.8 Flash (high) is stronger in composite, human preference, knowledge, long context, maths, multimodal, reasoning.
- Muse Spark is stronger in agents & tools, coding, instruction following.
At a glance
| Spec | Gemini 3.8 Flash | Muse Spark |
|---|---|---|
| Developer | Meta | |
| Released | 2 Sept 2026 | 8 Apr 2026 |
| Context window (tokens) | 1,048,576 | 262,144 |
| Compared at | Gemini 3.8 Flash (high) | Muse Spark |
| Open weights | No | No |
| Price in / out / cached input per 1M | $0.750 / $3.75 / $0.075 | – |
| 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 | Leader |
|---|---|---|---|
| Reasoning | 68.2 | 65.3 | Gemini 3.8 Flash |
| Coding | 63.5 | 65.0 | Muse Spark |
| Agents & tools | 50.9 | 66.1 | Muse Spark |
| Maths | 62.4 | 59.1 | Gemini 3.8 Flash |
| Knowledge | 68.4 | 63.3 | Gemini 3.8 Flash |
| Instruction following | – | 77.3 | not comparable |
| Human preference | 69.1 | 68.3 | level |
| Multimodal | 67.7 | 64.5 | Gemini 3.8 Flash |
| Long context | 65.7 | 64.0 | Gemini 3.8 Flash |
| Composite | 75.3 | 64.5 | Gemini 3.8 Flash |
Where sources disagree
Across the 29 benchmarks both have, Gemini 3.8 Flash leads 25, Muse Spark leads 4. Every overall index that rates both puts Gemini 3.8 Flash ahead.
| Overall index | Gemini 3.8 Flash (high) | Muse Spark | Leader |
|---|---|---|---|
| BenchLeader Index | 64.4 | 64.3 | neck and neck |
| AA Intelligence Index v4.3.2 | 40.9 | 31.3 | Gemini 3.8 Flash |
| Arena Text | 1496 | 1489 | 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 |
|---|---|---|
| Blended price per 1M tokens, until 31 Dec 2026 | $1.50 | – |
| Input / output per 1M | $0.750 / $3.75 | – / – |
| Blended price per 1M from 1 Jan 2027 | $3.00 | – |
| Input / output per 1M from 1 Jan 2027 | $1.50 / $7.50 | – |
| Cached input per 1M | $0.075 | – |
| Price per task: chat reply | $0.0014 | – |
| Price per task: summarize a 30-page report | $0.011 | – |
| Price per task: code edit | $0.010 | – |
| Price per task: agentic coding session | $0.060 | – |
| Price per task: structured extraction | $0.0023 | – |
| Cost to run a full benchmark suite | $1.24 | – |
| Output speed | 141 tok/s | – |
| Time to first answer | 25.1 s | – |
| Time to a complete answer | 28.7 s | – |
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 scores 64.3. 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.
| Metric | Publisher | Gemini 3.8 Flash (high) | Muse Spark |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 64.4 | 64.3 |
| Agents & tools score | BenchLeader | 50.9 | 66.1 |
| Coding score | BenchLeader | 63.5 | 65.0 |
| Composite score | BenchLeader | 75.3 | 64.5 |
| Human preference score | BenchLeader | 69.1 | 68.3 |
| Knowledge score | BenchLeader | 68.4 | 63.3 |
| Long context score | BenchLeader | 65.7 | 64.0 |
| Maths score | BenchLeader | 62.4 | 59.1 |
| Multimodal score | BenchLeader | 67.7 | 64.5 |
| Reasoning score | BenchLeader | 68.2 | 65.3 |
| Instruction following score | BenchLeader | – | 77.3 |
| Blended price $/M | BenchLeader | $1.50 | – |
| Output speed | BenchLeader | 141 tok/s | – |
| Time to first answer | BenchLeader | 25.1 s | – |
| Context window | BenchLeader | 1,048,576 tokens | 262,144 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 95.4% | 89.8% |
| Humanity's Last Exam | Scale AI / CAIS | 44.5%† | 40.6% |
| Arena Hard Prompts | Arena (LMArena) | 1517 | 1506 |
| LiveBench 2.0 Reasoning | LiveBench | 89.3%† | – |
| LiveBench 1.0 Reasoning | LiveBench | 89.3% | – |
| GPQA Diamond (AA) | Artificial Analysis | 95.3% | 88.4% |
| Humanity's Last Exam (AA) | Artificial Analysis | 47.8% | 40.7% |
| GPQA Diamond (Vals) | Vals AI | 94.4% | 89.7% |
| 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% | 11.3% |
| MysteryMechanism | Vals AI | 36.5% | – |
| Chess Puzzles | Epoch AI Benchmarking Hub | 58.0% | – |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 47.0% | – |
| LMCA | Epoch AI Benchmarking Hub | 51.5%† | – |
| DTBench | Epoch AI Benchmarking Hub | 95.7%† | – |
| Coding | |||
| SciCode | SciCode | 56.6% | 51.5% |
| WeirdML | WeirdML | 84.8% | – |
| FrontierCode | Cognition | 41.2%† | – |
| Arena Coding | Arena (LMArena) | 1528 | 1529 |
| Arena WebDev | Arena (LMArena) | 1585 | – |
| LiveBench 2.0 Coding | LiveBench | 82.2%† | – |
| LiveBench 1.0 Coding | LiveBench | 72.5% | – |
| SciCode (AA) | Artificial Analysis | 56.6% | – |
Show all 152 benchmarks
| Metric | Publisher | Gemini 3.8 Flash (high) | Muse Spark |
|---|---|---|---|
| Coding | |||
| LiveCodeBench | Vals AI | 89.5% | – |
| IOI | Vals AI | 56.9% | – |
| SWE-bench (Vals) | Vals AI | 80.0% | 74.4% |
| SWE-Bench Pro | Scale AI SEAL | – | 55.0% |
| Code Migration | Vals AI | 36.5% | – |
| Code Migration v1.1 | Vals AI | 38.6% | – |
| ProgramBench | Vals AI | 1.0% | – |
| 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% | 19.7% |
| SWE-Bench Pro (private) | Scale AI SEAL | – | 55.0% |
| SWE Atlas: Codebase QnA | Scale AI SEAL | 47.0%† | 24.2% |
| SWE Atlas: Refactoring | Scale AI SEAL | 44.8%† | – |
| SWE Atlas: Test Writing | Scale AI SEAL | 53.7%† | 31.1% |
| Surface Evolver Bench | Epoch AI Benchmarking Hub | 76.9% | – |
| DeepSWE v1.1 | Epoch AI Benchmarking Hub | 73.8% | – |
| CursorBench | Cursor | 39.6% | – |
| ALE-Bench | Epoch AI Benchmarking Hub | 1269.7 | – |
| FrontierSWE | Epoch AI Benchmarking Hub | 19.6% | – |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 19.7% | – |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | 87.6% | 62.2% |
| Startrise Frontend | Startrise | 64.6%† | – |
| 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%† | – |
| Arena Agent | Arena (LMArena) | 3.6 | – |
| LiveBench Long Agentic | LiveBench | 30.1%† | – |
| LiveBench Browser | LiveBench | 64.0%† | – |
| LiveBench Agentic Coding | LiveBench | 54.2% | – |
| Terminal-Bench Hard | Artificial Analysis | – | 45.5% |
| τ²-Bench Telecom (AA) | Artificial Analysis | – | 91.5% |
| Terminal-Bench 2.1 (Vals) | Vals AI | 81.3% | – |
| MCP Atlas | Scale AI SEAL | – | 82.2% |
| HiL-Bench | Scale AI SEAL | 41.5%† | – |
| GDPval-AA v2.1 | Artificial Analysis | 46.8% | – |
| τ³-Banking (AA) | Artificial Analysis | 45.0% | – |
| 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% | – |
| Finance Agent v2 | Vals AI | 61.4% | – |
| 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% | – |
| Legal Research Bench | Vals AI | 38.9% | – |
| SkillsBench | Vals AI | 58.0% | – |
| SREBench | Vals AI | 11.1% | – |
| Tax Agent Bench | Vals AI | 32.1% | – |
| Terminal-Bench 2.0 (Vals) | Vals AI | – | 59.5% |
| Terminal-Bench 4.0 (Vals) | Vals AI | 19.7% | – |
| 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% | – |
| GDP.pdf (AA) | Artificial Analysis | 21.0% | – |
| Harvey LAB-AA v1.1 | Harvey | 0.0% | – |
| 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% | 88.9% |
| ProofBench | Vals AI | 48.0%† | 17.0% |
| LiveBench Mathematics | LiveBench | 91.6% | – |
| AIME (Vals) | Vals AI | – | 96.9% |
| Arena Maths | Arena (LMArena) | 1526 | 1467 |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 69.7% | – |
| LiveBench 2.0 Data Analysis | LiveBench | 54.0%† | – |
| LiveBench Research | LiveBench | 79.1%† | – |
| LiveBench 1.0 Data Analysis | LiveBench | 54.0% | – |
| AA-Omniscience | Artificial Analysis | 29.6 | 7.2 |
| MMLU-Pro | Vals AI | 90.2% | 87.3% |
| LegalBench | Vals AI | 87.0% | 84.2% |
| CorpFin | Vals AI | – | 65.1% |
| TaxEval | Vals AI | 74.5% | 77.7% |
| PRBench Finance | Scale AI SEAL | 49.5%† | 52.4% |
| PRBench Legal | Scale AI SEAL | 48.9%† | 52.3% |
| MultiNRC | Scale AI SEAL | – | 59.0% |
| BioMysteryBench | Vals AI | 62.2% | – |
| CaseLaw v2 | Vals AI | – | 63.1% |
| Excel Modeling Benchmark | Vals AI | 72.2% | – |
| Excel Modeling Benchmark v1.1 | Vals AI | 72.9% | – |
| MedCode | Vals AI | 48.1% | 51.3% |
| MedScribe | Vals AI | 84.5% | 85.9% |
| Public Benefits Bench v1.1 | Vals AI | 65.3% | – |
| GDP.pdf | Epoch AI Benchmarking Hub | 23.2% | – |
| AA-Omniscience: accuracy | Artificial Analysis | 54.6% | 49.6% |
| AA-Omniscience: non-hallucination | Artificial Analysis | 44.8% | 15.8% |
| Instruction following | |||
| LiveBench Language | LiveBench | 87.8% | – |
| LiveBench Instruction Following | LiveBench | 81.4% | – |
| IFBench | Artificial Analysis | – | 75.9% |
| MultiChallenge | Scale AI SEAL | – | 75.5% |
| TutorBench | Scale AI SEAL | – | 68.5% |
| Arena Instruction Following | Arena (LMArena) | 1490 | 1465 |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1496 | 1489 |
| Arena Creative Writing | Arena (LMArena) | 1485 | 1464 |
| Arena Multi-turn | Arena (LMArena) | 1504 | 1494 |
| Arena Longer Queries | Arena (LMArena) | 1510 | 1476 |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | 1315 | 1306 |
| LiveBench Design | LiveBench | 72.7%† | – |
| MMMU-Pro | Artificial Analysis | 85.6% | 80.5% |
| MMMU-Pro (official) | MMMU | – | 80.4%† |
| MMMU-Pro (Vals) | Vals AI | 89.1% | 87.4% |
| MortgageTax | Vals AI | 65.3% | – |
| SAGE | Vals AI | 35.1% | – |
| 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% | 78.0% |
| Arena Document | Arena (LMArena) | – | 1467 |
| MLCR | Artificial Analysis | 10.6% | – |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 157.4† | 152.0 |
| LiveBench 2.0 | LiveBench | 67.3%† | – |
| LiveBench 1.0 | LiveBench | 75.8% | – |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 40.9 | 31.3 |
| 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 Router Index | Vals AI | 56.0%† | – |
| AA Cyber Index | Artificial Analysis | 25.1 | – |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | – | 20.2% |
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…).
- Gemini 3.8 Flash (high): 1 score revision.
- Gemini 3.8 Flash (high): 3 score revisions.
- Gemini 3.8 Flash (high): BenchLeader Index 63.7 → 64.5.
- Gemini 3.8 Flash (high): 1 new result (AudioMC (text output)).
- Gemini 3.8 Flash (high): 1 new result (SREBench); 2 score revisions.
- Gemini 3.8 Flash (high): 2 score revisions.
- Gemini 3.8 Flash (high): 1 new result (Analyst Agent (AA)); 1 score revision.
- Muse Spark: 1 new result (PRBench Legal).
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 vs Claude Opus 5.5
- Muse Spark vs Gemini 4 Argon
- Muse Spark vs Muse Wonder Full
- Muse Spark vs Claude Fable 5.1
- Gemini 3.7 Flash vs Muse Spark
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
Gemini 3.8 Flash vs Muse Spark: questions
- Is Gemini 3.8 Flash better than Muse Spark?
- Gemini 3.8 Flash (high) and Muse Spark are neck and neck on quality (64.4 vs 64.3, within the ±5.0 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.
- Is Gemini 3.8 Flash better than Muse Spark for coding?
- Muse Spark scores higher in coding (65 vs 64 on the category index, where 50 is average). On SciCode, the top shared coding benchmark, it is 56.6% for Gemini 3.8 Flash against 51.5% for Muse Spark.
- Is Gemini 3.8 Flash better than Muse Spark for agents and tool use?
- Muse Spark scores higher in agentic tasks (66 vs 51 on the category index, where 50 is average).
- Which is better for long documents?
- Gemini 3.8 Flash scores higher on long-context benchmarks (66 vs 64). Gemini 3.8 Flash accepts more context: 1,048,576 against 262,144 tokens for Muse Spark.
- Do independent benchmarks agree on Gemini 3.8 Flash vs Muse Spark?
- Across the 29 benchmarks both have, Gemini 3.8 Flash leads 25, Muse Spark leads 4. 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.