Mistral Large 4 vs Muse Spark 1.3
Full profiles: Mistral Large 4 (Mistral AI) and Muse Spark 1.3 (Meta): every benchmark, price and rank.
Updated · Data from 10 sources
As of 16 Nov 2026, Muse Spark 1.3 is ahead of Mistral Large 4 on quality (61.6 vs 52.9 on the BenchLeader Index), but Mistral Large 4 is 1.9× cheaper at $1.05 vs $2.00 per 1M tokens blended. Muse Spark 1.3 leads in every category we measure both in.
Key facts (as of 16 Nov 2026)
- Mistral Large 4 scores 52.9 on the BenchLeader Index and Muse Spark 1.3 scores 61.6 (BenchLeader, 16 Nov 2026).
- Mistral Large 4 costs $1.05 per 1M tokens blended (list price, 16 Nov 2026).
- Muse Spark 1.3 costs $2.00 per 1M tokens blended (list price, 16 Nov 2026).
- Of the 5 benchmarks both models have, Muse Spark 1.3 leads 5 (BenchLeader, 16 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 case | Pick | Why | Confidence |
|---|---|---|---|
| Agents & tool use | Muse Spark 1.3 | 61 vs 49 category score | High |
| Maths | Muse Spark 1.3 | 56 vs 54 category score; ProofBench 55.0% vs 10.0% | Medium |
| Reasoning | Muse Spark 1.3 | 71 vs 46 category score; LMCA 53.9% vs 35.8% | High |
| Knowledge | Muse Spark 1.3 | 81 vs 41 category score | High |
| Chat quality (human preference) | – | Only Mistral Large 4 has an Arena rating (60 category score) | Not comparable |
| Lowest cost | Mistral Large 4 | $1.05 vs $2.00 per 1M blended; agentic coding session $0.050 vs $0.092 | – |
| Fastest first answer | Muse Spark 1.3 | 2.6 s (Muse Spark 1.3) vs 40.9 s (Mistral Large 4) 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
- Muse Spark 1.3 leads on quality: 61.6 vs 52.9.
- Muse Spark 1.3 is stronger in agents & tools, knowledge, maths, reasoning.
- Mistral Large 4 is 1.9× cheaper ($1.05 vs $2.00 per 1M blended).
- Muse Spark 1.3 streams 1.7× faster (163 vs 97 tokens per second).
At a glance
| Spec | Mistral Large 4 | Muse Spark 1.3 |
|---|---|---|
| Developer | Mistral AI | Meta |
| Released | 6 Oct 2026 | 2 Sep 2026 |
| Context window (tokens) | 1,048,576 | 1,048,576 |
| Compared at | Mistral Large 4 | Muse Spark 1.3 |
| Open weights | Yes | No |
| Price in / out / cached input per 1M | $0.700 / $2.10 / $0.070 | $1.25 / $4.25 / $0.150 |
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 | Mistral Large 4 | Muse Spark 1.3 | Leader |
|---|---|---|---|
| Reasoning | 46.2 | 71.0 | Muse Spark 1.3 |
| Coding | 53.8 | – | not comparable |
| Agents & tools | 48.8 | 61.3 | Muse Spark 1.3 |
| Maths | 54.2 | 56.3 | Muse Spark 1.3 |
| Knowledge | 40.7 | 81.2 | Muse Spark 1.3 |
| Human preference | 59.7 | – | not comparable |
| Multimodal | 58.0 | – | not comparable |
| Long context | 65.3 | – | not comparable |
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.
Not drawn, measured for fewer than two of these models: Coding, Instruction following, Long context, Multimodal, Human preference.
Where sources disagree
Across the 5 benchmarks both have, Mistral Large 4 leads 0, Muse Spark 1.3 leads 5. Every overall index that rates both puts Muse Spark 1.3 ahead.
| Overall index | Mistral Large 4 | Muse Spark 1.3 | Leader |
|---|---|---|---|
| BenchLeader Index | 52.9 | 61.6 | Muse Spark 1.3 |
| AA Intelligence Index v5.0.1 | 25.3 | 36.6† | Muse Spark 1.3 |
| Arena Text | 1420 | 1497† | Muse Spark 1.3 |
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.
| Measure | Mistral Large 4 | Muse Spark 1.3 |
|---|---|---|
| Blended price per 1M tokens | $1.05 | $2.00 |
| Input / output per 1M | $0.700 / $2.10 | $1.25 / $4.25 |
| Cached input per 1M | $0.070 | $0.150 |
| Price per task: chat reply | $0.0009 | $0.0018 |
| Price per task: summarize a 30-page report | $0.0097 | $0.018 |
| Price per task: code edit | $0.0074 | $0.014 |
| Price per task: agentic coding session | $0.050 | $0.092 |
| Price per task: structured extraction | $0.0018 | $0.0034 |
| Agentic coding session, input mostly cached | $0.022 | $0.043 |
| Cost per benchmark task (AA Index) | $4.21 | – |
| Output tokens per task (AA Index) | 135k | – |
| Of which reasoning | 102k | – |
| Time per task (AA Index) | 23 min | – |
| Output speed | 97 tok/s | 163 tok/s |
| Time to first answer | 40.9 s | 2.6 s |
| Time to a complete answer, last measured 13 Nov 2026 | 119.0 s | – |
Each model is compared at its best-ranked reasoning-effort setting. Mistral Large 4 scores 52.9 and takes 41 s to its first answer token; Mistral Large 4 (high) scores 48.3 in 45 s, Mistral Large 4 (medium) scores 45.9 in 27 s. Muse Spark 1.3 scores 61.6 and takes 3 s to its first answer token; Muse Spark 1.3 (max) scores 60.6 in 31 s, Muse Spark 1.3 (xhigh) scores 58.1 in 11 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
142 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 | Mistral Large 4 | Muse Spark 1.3 |
|---|---|---|---|
| BenchLeader Index | BenchLeader | 52.9 | 61.6 |
| Agents & tools score | BenchLeader | 48.8 | 61.3 |
| Coding score | BenchLeader | 53.8 | – |
| Human preference score | BenchLeader | 59.7 | – |
| Knowledge score | BenchLeader | 40.7 | 81.2 |
| Long context score | BenchLeader | 65.3 | – |
| Maths score | BenchLeader | 54.2 | 56.3 |
| Multimodal score | BenchLeader | 58.0 | – |
| Reasoning score | BenchLeader | 46.2 | 71.0 |
| Blended price $/M | BenchLeader | $1.05 | $2.00 |
| Output speed | BenchLeader | 97 tok/s | 163 tok/s |
| Time to first answer | BenchLeader | 40.9 s | 2.6 s |
| Context window | BenchLeader | 1,048,576 tokens | 1,048,576 tokens |
| Reasoning | |||
| GPQA Diamond | Epoch AI Benchmarking Hub | 88.1%† | – |
| SimpleBench | SimpleBench | – | 81.8% |
| Arena Hard Prompts | Arena (LMArena) | 1453 | 1517† |
| LiveBench 2.0 Reasoning | LiveBench | 85.2%† | 89.7%† |
| LiveBench 1.0 Reasoning | LiveBench | 83.9%† | 89.7%† |
| GPQA Diamond (AA) | Artificial Analysis | – | 93.5%† |
| Humanity's Last Exam (AA) | Artificial Analysis | 35.0% | 48.7%† |
| HLE-Diamond (AA) | Artificial Analysis | 15.1% | 33.7%† |
| CritPt | Artificial Analysis | 10.6% | 24.9%† |
| CritPt v2 hard subset (AA) | Artificial Analysis | 24.5% | 48.0%† |
| MysteryMechanism | Vals AI | 12.2%† | 36.0%† |
| HLE-Diamond (Scale) | Scale AI SEAL | – | 25.4% |
| Arena Expert | Arena (LMArena) | 1464 | 1521† |
| Chess Puzzles | Epoch AI Benchmarking Hub | 33.0%† | 37.0%† |
| Mystery Game Puzzles | Epoch AI Benchmarking Hub | 17.0%† | 25.0%† |
| LMCA | Epoch AI Benchmarking Hub | 35.8% | 53.9% |
| DTBench | Epoch AI Benchmarking Hub | 88.2% | 96.5% |
| ForecastBench | ForecastBench | – | 65.5%† |
| BTF-3 | Epoch AI Benchmarking Hub | – | 14.1%† |
| Coding | |||
| SciCode | SciCode | 54.2% | 58.8%† |
| FrontierCode | Cognition | 39.4%† | – |
| Arena Coding | Arena (LMArena) | 1484 | 1534† |
| Arena WebDev | Arena (LMArena) | 1565 | 1655† |
| LiveBench 2.0 Coding | LiveBench | 79.4%† | 84.4%† |
| LiveBench 1.0 Coding | LiveBench | 77.2%† | 81.1%† |
Show all 142 benchmarks
| Metric | Publisher | Mistral Large 4 | Muse Spark 1.3 |
|---|---|---|---|
| Coding | |||
| IOI | Vals AI | 45.3%† | 56.6%† |
| Code Migration | Vals AI | 30.6%† | 47.4%† |
| ProgramBench | Vals AI | – | 2.5%† |
| SWE-bench Multimodal | Vals AI | 33.1%† | 43.1%† |
| Vibe Code Bench 1-100 | Vals AI | 14.3%† | 20.5%† |
| Vibe Code Bench v1.1 | Vals AI | 78.4%† | 85.9%† |
| SWE Atlas v1.1 | Scale AI SEAL | 45.2% | – |
| SWE Atlas v1.1: Codebase QnA | Scale AI SEAL | 61.3% | – |
| SWE Atlas v1.1: Test Writing | Scale AI SEAL | 40.0% | – |
| SWE Atlas v1.1: Refactoring | Scale AI SEAL | 34.3% | – |
| MirrorCode | Epoch AI Benchmarking Hub | 40.0%† | 54.4%† |
| Surface Evolver Bench | Epoch AI Benchmarking Hub | 28.1% | – |
| CursorBench | Cursor | – | 41.6%† |
| ALE-Bench | Epoch AI Benchmarking Hub | 1213.2 | 1688.3† |
| FrontierSWE | Epoch AI Benchmarking Hub | – | 25.8%† |
| WeirdML v3 | WeirdML | 4.5%† | 6.7%† |
| Terminal-Bench 4.0 (AA) | Artificial Analysis | 26.8% | 33.3%† |
| Terminal-Bench 2.1 (AA) | Artificial Analysis | – | 84.3%† |
| Startrise Frontend | Startrise | – | 74.7% |
| GameBench 2 Overall | DuelLab GameBench 2 | – | 57.7 |
| GameBench 2 by reasoning setting | DuelLab GameBench 2 | 57.6† | 68.5† |
| Design Arena Website | Design Arena | 1258 | 1353† |
| FrontierCode 1.1 (AA) | Artificial Analysis | 41.5% | 40.6%† |
| FrontierCode 2.0 (AA) | Artificial Analysis | 13.6% | 23.1%† |
| Agents & tools | |||
| Terminal-Bench | Terminal-Bench | 27.6%† | 14.8%† |
| APEX-Agents | Mercor | 51.6%† | 58.6% |
| Arena Agent | Arena (LMArena) | -5.4 | 2.2† |
| LiveBench Long Agentic | LiveBench | 24.7%† | 47.9%† |
| LiveBench Browser | LiveBench | 17.4%† | 30.9%† |
| LiveBench Agentic Coding | LiveBench | 57.2%† | 64.1%† |
| Terminal-Bench 2.1 (Vals) | Vals AI | – | 79.0%† |
| HiL-Bench | Scale AI SEAL | – | 66.9% |
| GDPval-AA v2.1, normalised score | Artificial Analysis | 46.1% | – |
| GDPval-AA v2.1 | Artificial Analysis | 1431 | 1681† |
| τ³-Banking (AA) | Artificial Analysis | – | 50.5%† |
| ITBench SRE (AA) | Artificial Analysis | – | 33.2%† |
| Analyst Agent (AA) | Artificial Analysis | – | 37.5%† |
| CUA-bench | Vals AI | – | 5.8%† |
| CyberBench | Vals AI | – | 72.7%† |
| Finance Agent v2 | Vals AI | 54.7%† | 60.0%† |
| Finance Agent v2.1 | Vals AI | 61.4%† | – |
| Harvey's Legal Agent Benchmark v1.1 | Vals AI | 17.5%† | – |
| Harvey's Legal Agent Benchmark v1 | Vals AI | 15.8%† | 23.8%† |
| Legal Research Bench | Vals AI | 31.7%† | 55.3%† |
| SREBench | Vals AI | – | 3.8%† |
| Tax Agent Bench | Vals AI | 30.4%† | 42.4%† |
| Terminal-Bench 4.0 (Vals) | Vals AI | 27.8%† | 24.8%† |
| Terminal-Bench Science | Vals AI | – | 10.0%† |
| Arena Agent Task Completion | Arena (LMArena) | -4.7 | 3.7† |
| AutomationBench | Artificial Analysis | 59.9% | 57.9%† |
| GDP.pdf (AA) | Artificial Analysis | 18.6% | 26.6%† |
| Harvey LAB-AA v1.1 | Harvey | 3.1% | 8.9%† |
| AA-Briefcase v1.1 | Artificial Analysis | 1393 | 1581† |
| Design Arena Agentic | Design Arena | – | 1283† |
| Terminal-Bench-Science 0.1 (AA) | Artificial Analysis | 4.8% | 10.9%† |
| CWE-Bench (AA) | Artificial Analysis | 50.8% | 60.8%† |
| DeepSec-Bench (AA) | Artificial Analysis | 16.0% | 12.5%† |
| CyberGym end-to-end (AA) | Artificial Analysis | 81.7% | 59.5%† |
| MKA (AA) | Artificial Analysis | 35.1%† | – |
| Maths | |||
| FrontierMath Tiers 1–3 | Epoch AI Benchmarking Hub | 58.6%† | 74.0%† |
| FrontierMath Tier 4 | Epoch AI Benchmarking Hub | 26.8%† | 46.3%† |
| OTIS Mock AIME | Epoch AI Benchmarking Hub | 98.3%† | 99.2%† |
| ProofBench | Vals AI | 10.0% | 55.0% |
| LiveBench Mathematics | LiveBench | 93.6%† | 96.0%† |
| Arena Maths | Arena (LMArena) | 1459 | 1506† |
| Knowledge | |||
| SimpleQA Verified | Epoch AI Benchmarking Hub | 20.0%† | – |
| LiveBench 2.0 Data Analysis | LiveBench | 76.6%† | 79.6%† |
| LiveBench Research | LiveBench | 80.3%† | 82.5%† |
| LiveBench 1.0 Data Analysis | LiveBench | 76.5%† | 79.6%† |
| AA-Omniscience v1.1 | Artificial Analysis | -7.5 | 22.4† |
| PRBench Finance | Scale AI SEAL | – | 59.5% |
| PRBench Legal | Scale AI SEAL | – | 61.6% |
| BioMysteryBench | Vals AI | 67.0%† | – |
| Excel Modeling Benchmark | Vals AI | 56.2%† | 67.4%† |
| Excel Modeling Benchmark v1.1 | Vals AI | 69.0%† | – |
| MedCode | Vals AI | 40.7%† | – |
| MedScribe | Vals AI | 80.4%† | – |
| Access to Justice Benchmark | Vals AI | – | 72.2%† |
| Financial Coaching Bench | Vals AI | – | 70.3%† |
| Immigration Bench | Vals AI | 63.7%† | 64.9%† |
| DrugDiscoveryBench | Scale AI SEAL | – | 62.2%† |
| GDP.pdf | Epoch AI Benchmarking Hub | – | 27.6% |
| AA-Omniscience v1.1: accuracy | Artificial Analysis | 23.9% | 38.0%† |
| AA-Omniscience v1.1: non-hallucination | Artificial Analysis | 58.7% | 74.8%† |
| Instruction following | |||
| LiveBench Language | LiveBench | 49.6%† | 82.8%† |
| LiveBench Instruction Following | LiveBench | 64.8%† | 78.0%† |
| Arena Instruction Following | Arena (LMArena) | 1418 | 1485† |
| Human preference | |||
| Arena Text | Arena (LMArena) | 1420 | 1497† |
| EQ-Bench Creative Writing v3 | EQ-Bench | – | 1907 |
| Arena Creative Writing | Arena (LMArena) | 1359 | 1468† |
| Arena Multi-turn | Arena (LMArena) | 1429 | 1493† |
| Arena Longer Queries | Arena (LMArena) | 1420 | 1498† |
| Multimodal | |||
| Arena Vision | Arena (LMArena) | 1244 | 1310† |
| LiveBench Design | LiveBench | 76.3%† | 74.8%† |
| MMMU-Pro | Artificial Analysis | 76.4% | 82.0%† |
| Humanity's Sixth Sense | Scale AI SEAL | – | 37.4%† |
| GeoBench | GeoBench | – | 86.0% |
| Furniture Assembly | Epoch AI Benchmarking Hub | 20.8%† | – |
| VIALS-AA | Handshake AI | 20.5%† | – |
| Code2Video-AA | Artificial Analysis | 931 | 1019† |
| AA-3D | Artificial Analysis | 882 | 1032† |
| Long context | |||
| AA-LCR v1.1 | Artificial Analysis | 81.3% | 83.0%† |
| Arena Document | Arena (LMArena) | – | 1474† |
| MLCR | Artificial Analysis | 7.8% | 13.9%† |
| Composite | |||
| Epoch Capabilities Index | Epoch AI Benchmarking Hub | 154.6 | 158.2 |
| LiveBench 2.0 | LiveBench | 60.3%† | 68.6%† |
| LiveBench 1.0 | LiveBench | 71.8%† | 81.6%† |
| AA Intelligence Index v5.0.1 | Artificial Analysis | 25.3 | 36.6† |
| AA Intelligence Index v4.3.2 | Artificial Analysis | 38.4 | 48.1† |
| AA Progress Index v1 | Artificial Analysis | 312.4 | 324.5† |
| Vals Finance Index | Vals AI | 56.9%† | – |
| Vals RSI Index | Vals AI | – | 19.6%† |
| Vals Legal Index | Vals AI | 65.6%† | – |
| AA Cyber Index | Artificial Analysis | 49.5 | 44.3† |
| Safety & honesty | |||
| FORTRESS | Scale AI SEAL | 23.1% | – |
| DistressBench | Scale AI SEAL | 77.0% | 84.9% |
| Metadata | |||
| AA Openness Index | Artificial Analysis | 38.9† | – |
Data as of 2026-11-16. Best configuration of each model; every score links to its source on the model pages.
DuelLab GameBench 2, release gb2-20261111-7b598bb13de4 (https://benchmarks.duellab.org/releases/gb2-20261111-7b598bb13de4/), CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/). Scores mapped to BenchLeader model names; not endorsed by DuelLab.
What changed
- Mistral Large 4: BenchLeader Index 52.2 → 52.9.
- Muse Spark 1.3: BenchLeader Index 60.2 → 61.6.
- Mistral Large 4: 1 new result (GDPval-AA v2.1).
- Mistral Large 4: 1 score revision.
- Mistral Large 4: 2 score revisions.
- Muse Spark 1.3: 1 score revision.
- Muse Spark 1.3: BenchLeader Index 59.2 → 60.2.
- Muse Spark 1.3: 2 new results (SimpleBench, GeoBench).
- Mistral Large 4: 6 score revisions.
- Mistral Large 4: BenchLeader Index 52.7 → 52.2.
Related comparisons
- Mistral Large 4 vs MiniMax M3.1 Flash
- Mistral Large 4 vs Muse Ember
- Mistral Large 4 vs Mistral Large 4.0 OSS
- Muse Spark 1.3 vs Claude Fable 5.2
- Muse Spark 1.3 vs Gemini 4 Carbon
- Muse Spark 1.3 vs Claude Opus 5.5
- Muse Spark 1.3 vs GPT-6 Astra
- Muse Spark 1.3 vs Claude Fable 5.1
Rankings: Best LLM overall · Best LLM for agents · Best cheap LLMs
Mistral Large 4 vs Muse Spark 1.3: questions
- Is Muse Spark 1.3 better than Mistral Large 4?
- Muse Spark 1.3 leads on quality: 61.6 vs 52.9. The BenchLeader Index combines every independent quality benchmark; Muse Spark 1.3 is ahead overall as of 16 Nov 2026, but check the category scores for your use.
- Mistral Large 4 vs Muse Spark 1.3: which is cheaper, and will that change?
- Mistral Large 4 is cheaper today: $1.05 against $2.00 per million tokens, blended at three input tokens per output token. No price change has been announced for either.
- Which is faster, Mistral Large 4 or Muse Spark 1.3?
- Muse Spark 1.3 streams faster (163 vs 97 output tokens per second, Artificial Analysis 7-day median).
- Is Mistral Large 4 or Muse Spark 1.3 better for agents and tool use?
- Muse Spark 1.3 scores higher in agentic tasks (61 vs 49 on the category index, where 50 is average).
- Which is better for long documents?
- Both accept 1,048,576 tokens of context.
More questions (3)
- Which has lower latency?
- Muse Spark 1.3 answers first: 2.6 s against 40.9 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 Mistral Large 4 vs Muse Spark 1.3?
- Across the 5 benchmarks both have, Mistral Large 4 leads 0, Muse Spark 1.3 leads 5. Every overall index that rates both puts Muse Spark 1.3 ahead.
- When was Mistral Large 4 released?
- Mistral Large 4 was released on 6 Oct 2026.