GPT-5.1-Codex vs Muse Spark Open
Muse Spark Open leads GPT-5.1-Codex on coding, 47.4 to 15.3 on the Vibe Coding Index, and Muse Spark Open costs 2.4x less per output token ($4.25 vs $10.00 per million). Updated October 21, 2026; 9 benchmarks have a result for both.
GPT-5.1-Codex or Muse Spark Open: which to pick
Pick Muse Spark Open for coding: it scores 47.4 on the Vibe Coding Index against 15.3 for GPT-5.1-Codex.
GPT-5.1-Codex is neither cheaper nor larger in context, and leads no benchmark both models were measured on.
- Shared results
- 9
- GPT-5.1-Codex only
- 17
- Muse Spark Open only
- 19
- Like-for-like categories
- 4 of 9
Only benchmarks that tested both models count toward a pick; a result only one model has is shown but not compared.
Which one for your work
Each card is decided by one number both models carry. Where only one has it, the card says so and makes no call.
Coding
Vibe Coding Index, six public coding benchmarks
Muse Spark Open
Muse Spark Open scores 47.4 against 15.3.
2 and 4 benchmarks behind the scores
Intelligence
AA Intelligence Index
No call
Only GPT-5.1-Codex has a AA Intelligence Index result, 23.7.
Directional only
Web design
Design Arena: websites
Muse Spark Open
Muse Spark Open leads, 1317 against 1162.
Same board, both measured
General
Vals Index
No call
Only Muse Spark Open has a Vals Index result, 48.6%.
Directional only
Long documents
Listed context window
Muse Spark Open
Muse Spark Open takes 1.05M tokens against 400K.
Listed by OpenRouter
Everyday cost
1K input + 500 output tokens
Muse Spark Open
GPT-5.1-Codex $0.0063, Muse Spark Open $0.0034 per turn.
List prices
Cost per solved task
One SWE-bench Verified task, solved
No call
Only GPT-5.1-Codex has the number, $0.892.
Directional only
At a glance
- Coding index
- GPT-5.1-Codex 15.3 from 2 benchmarks, Muse Spark Open 47.4 from 4 benchmarks.
- Widest category
- Coding, 31.7 points apart on average over 4 shared benchmarks.
- Widest single gap
- Vibe Code Bench (Vals AI): GPT-5.1-Codex 13.1% against Muse Spark Open 76.2%, 63.1 points apart on a 0 to 100 scale.
- Output price
- GPT-5.1-Codex $10.00 against Muse Spark Open $4.25 per million output tokens, 2.4x apart.
- Context window
- GPT-5.1-Codex takes 400K tokens, Muse Spark Open 1.05M.
Benchmark by benchmark
First the score: boards each model leads, per category, where both have a result. Then every board, a category to a fold; bars are each result on a 0 to 100 scale, so compare the two in a row, not one row with another.
| Category | GPT-5.1-Codex | Bars | Muse Spark Open | Ties |
|---|---|---|---|---|
| Coding | 0 | 4 | ||
| Reasoning | 0 | 2 | ||
| Web design | 0 | 2 | ||
| General | 0 | 1 | ||
| All shared boards | 0 | 9 |
CodingLike-for-likeSix of these boards feed the Vibe Coding Index04
| Benchmark | GPT-5.1-Codex | Muse Spark Open | Leader |
|---|---|---|---|
| SWE-bench Verified | 66.0% | Not measured | Only GPT-5.1-Codex measured |
| LiveBench coding | Not measured | 73.6% | Only Muse Spark Open measured |
| LMArena WebDev | 1337 | 1528 | Muse Spark Open |
| LiveCodeBench (Vals AI) | 85.5% | Not measured | Only GPT-5.1-Codex measured |
| Terminal-Bench 4 (Vals AI) | Not measured | 6.6% | Only Muse Spark Open measured |
| Vibe Code Bench (Vals AI) | 13.1% | 76.2% | Muse Spark Open |
| Code migration (Vals AI) | Not measured | 21.2% | Only Muse Spark Open measured |
| LiveCodeBench (Artificial Analysis run) | 84.9% | Not measured | Only GPT-5.1-Codex measured |
| SciCode | Not measured | 58.4% | Only Muse Spark Open measured |
| Terminal-Bench Hard (Artificial Analysis run) | 34.8% | Not measured | Only GPT-5.1-Codex measured |
| Terminal-Bench | 57.8% | Not measured | Only GPT-5.1-Codex measured |
| ALE-Bench | 1244.9 | 1590.1 | Muse Spark Open |
| LMArena WebDev: React | Not measured | 1529 | Only Muse Spark Open measured |
| LMArena WebDev: HTML | 1346 | 1495 | Muse Spark Open |
| Neither model has a result on the other 25 boards here | |||
IntelligenceDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | GPT-5.1-Codex | Muse Spark Open | Leader |
|---|---|---|---|
| AA Intelligence Index | 23.7 | Not measured | Only GPT-5.1-Codex measured |
| Epoch Capabilities Index | Not measured | 155.1 | Only Muse Spark Open measured |
Agentic workDirectional onlyPublic boards, shown as published, kept out of the index13 boards, none shared
| Benchmark | GPT-5.1-Codex | Muse Spark Open | Leader |
|---|---|---|---|
| Design Arena: agents building web apps | 1018 | Not measured | Only GPT-5.1-Codex measured |
| Design Arena: agents building full-stack apps | 1086 | Not measured | Only GPT-5.1-Codex measured |
| Design Arena: agents building mobile apps | 1191 | Not measured | Only GPT-5.1-Codex measured |
| LiveBench research | Not measured | 80.3% | Only Muse Spark Open measured |
| LiveBench browser | Not measured | 36.0% | Only Muse Spark Open measured |
| LiveBench long agentic | Not measured | 18.9% | Only Muse Spark Open measured |
| Finance Agent (Vals AI) | Not measured | 61.3% | Only Muse Spark Open measured |
| Tax Agent Bench (Vals AI) | Not measured | 26.3% | Only Muse Spark Open measured |
| Legal Research Bench (Vals AI) | Not measured | 38.5% | Only Muse Spark Open measured |
| Harvey's Legal Agent Benchmark (Vals AI) | Not measured | 25.0% | Only Muse Spark Open measured |
| Excel Modeling Benchmark (Vals AI) | Not measured | 53.7% | Only Muse Spark Open measured |
| τ²-Bench Telecom | 83.0% | Not measured | Only GPT-5.1-Codex measured |
| APEX-Agents | Not measured | 33.4% | Only Muse Spark Open measured |
| Neither model has a result on the other 28 boards here | |||
ReasoningLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | GPT-5.1-Codex | Muse Spark Open | Leader |
|---|---|---|---|
| LiveBench reasoning | Not measured | 73.7% | Only Muse Spark Open measured |
| GPQA Diamond (Artificial Analysis run) | 86.0% | 89.0% | Muse Spark Open |
| Humanity's Last Exam (Artificial Analysis run) | 25.7% | 43.9% | Muse Spark Open |
| Neither model has a result on the other 19 boards here | |||
MathDirectional onlyPublic boards, shown as published, kept out of the index2 boards, none shared
| Benchmark | GPT-5.1-Codex | Muse Spark Open | Leader |
|---|---|---|---|
| AA Math Index | 95.7 | Not measured | Only GPT-5.1-Codex measured |
| AIME 2025 (Artificial Analysis run) | 95.7% | Not measured | Only GPT-5.1-Codex measured |
| Neither model has a result on the other 11 boards here | |||
KnowledgeDirectional onlyPublic boards, shown as published, kept out of the index1 board, none shared
| Benchmark | GPT-5.1-Codex | Muse Spark Open | Leader |
|---|---|---|---|
| MMLU Pro (Artificial Analysis run) | 86.0% | Not measured | Only GPT-5.1-Codex measured |
| Neither model has a result on the other 17 boards here | |||
Web designLike-for-likePublic boards, shown as published, kept out of the index02
| Benchmark | GPT-5.1-Codex | Muse Spark Open | Leader |
|---|---|---|---|
| Design Arena: websites | 1162 | 1317 | Muse Spark Open |
| Design Arena: UI components | 1237 | Not measured | Only GPT-5.1-Codex measured |
| Design Arena: game dev | 1138 | 1294 | Muse Spark Open |
| Design Arena: data viz | 1213 | Not measured | Only GPT-5.1-Codex measured |
| Design Arena: all code categories | 1152 | Not measured | Only GPT-5.1-Codex measured |
| LiveBench design | Not measured | 60.3% | Only Muse Spark Open measured |
| Neither model has a result on the other 3 boards here | |||
GeneralLike-for-likePublic boards, shown as published, kept out of the index01
| Benchmark | GPT-5.1-Codex | Muse Spark Open | Leader |
|---|---|---|---|
| Vals Index | Not measured | 48.6% | Only Muse Spark Open measured |
| LiveBench data analysis | Not measured | 60.2% | Only Muse Spark Open measured |
| IFBench | 70.0% | Not measured | Only GPT-5.1-Codex measured |
| Long context reasoning (AA-LCR) | 69.3% | 78.3% | Muse Spark Open |
| Neither model has a result on the other 42 boards here | |||
Image generationNot comparablePublic boards, shown as published, kept out of the index0 boards, none shared
| Benchmark | GPT-5.1-Codex | Muse Spark Open | Leader |
|---|---|---|---|
| Neither model has a result on 5 boards here | |||
What each workload costs
Three fixed token mixes at each model's listed price, so per-token rates become a bill.
Chat turn
1K input + 500 output tokens
Muse Spark Open costs less
Repository review
50K input + 3K output tokens
Muse Spark Open costs less
Agent loop
200K input + 10K output tokens
Muse Spark Open costs less
Listed OpenRouter rates, without cache or batch discounts. A workload that does not fit a model's context window would need splitting.
Specification differences
The leading value in a row is marked; a row with a missing value names no leader. Our two rows are marked in red.
| Specification | OpenAI GPT-5.1-Codex | Meta Muse Spark Open |
|---|---|---|
| Maker | OpenAI | Meta |
| Weights | No public weights listed | Open weights |
| Released | November 13, 2025 | October 15, 2026 |
| Context window | 400K | 1.05M |
| Input $/Mtok | $1.25 | $1.25 |
| Output $/Mtok | $10.00 | $4.25 |
| Coding index | 15.3 | 47.4 |
| Independent measurements behind it | 2 | 4 |
| Cost per solved task | $0.892 | Not computable |
| Source | OpenRouter listing | OpenRouter listing |
Questions
Is GPT-5.1-Codex better than Muse Spark Open for coding?
Pick Muse Spark Open for coding: it scores 47.4 on the Vibe Coding Index against 15.3 for GPT-5.1-Codex. GPT-5.1-Codex is neither cheaper nor larger in context, and leads no benchmark both models were measured on.
Which is cheaper, GPT-5.1-Codex or Muse Spark Open?
GPT-5.1-Codex costs $1.25 per million input tokens and $10.00 per million output tokens; Muse Spark Open costs $1.25 and $4.25. Cost per solved task is known for GPT-5.1-Codex only.
Which has the bigger context window, GPT-5.1-Codex or Muse Spark Open?
Muse Spark Open, with 1.05M tokens against 400K.
How many benchmarks is the GPT-5.1-Codex vs Muse Spark Open comparison based on?
9 benchmarks have a result for both models as of October 21, 2026. GPT-5.1-Codex's coding index rests on 2 independent benchmarks and Muse Spark Open's on 4. Where only one model has a result, the page says so instead of naming a winner.