# GPT-5-Codex vs Muse Spark 1.2

> Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 37.9 on the Noometry Index.

- Canonical page: https://noometry.com/compare/gpt-5-codex-vs-muse-spark-1-2
- Last updated: 2026-10-11
- Shared benchmarks: 1

## Summary

- They share 1 benchmark with published results for both. GPT-5-Codex scores higher in 1 category and Muse Spark 1.2 in 2 categories; 3 gaps are clear of the uncertainty.
- The widest gap is in reasoning, where Muse Spark 1.2 leads 51.3 to 30.9.
- The biggest single-benchmark swing is WeirdML: 54.5% for GPT-5-Codex and 60.3% for Muse Spark 1.2.
- Muse Spark 1.2 is cheaper at $1.25 / $4.25 per million input/output tokens, against $1.25 / $10 for GPT-5-Codex.
- Muse Spark 1.2 accepts more context: 1.05M tokens versus 400K.

## Snapshot

| | GPT-5-Codex | Muse Spark 1.2 |
|---|---|---|
| Provider | OpenAI | Meta |
| Noometry Index | 37.9 | 50.3 |
| Rank | 192 | 48 |
| Context | 400K | 1.05M |
| Input $/M | $1.25 | $1.25 |
| Output $/M | $10 | $4.25 |
| Weights | Proprietary | Proprietary |

## Coding

- GPT-5-Codex: 42.4 (#103)
- Muse Spark 1.2: 49.2 (#51)

| Benchmark | GPT-5-Codex | Muse Spark 1.2 |
|---|---|---|
| WeirdML | 54.5% | 60.3% |
| DeepSWE | — | 54.9% |
| LMArena WebDev | — | 1533 |
| FrontierSWE | — | 12% |
| SciCode | — | 56.4% |
| LMArena Coding | — | 1495 |

## Agentic & Tool Use

- GPT-5-Codex: 31.0 (#72)
- Muse Spark 1.2: 29.4 (#87)

| Benchmark | GPT-5-Codex | Muse Spark 1.2 |
|---|---|---|
| Terminal-Bench | 44.3% | — |
| APEX-Agents | — | 36.4% |
| GDP.pdf | — | 16% |

## Reasoning

- GPT-5-Codex: 30.9 (#83)
- Muse Spark 1.2: 51.3 (#34)

| Benchmark | GPT-5-Codex | Muse Spark 1.2 |
|---|---|---|
| SimpleBench | — | 74.5% |
| Kagi LLM Benchmark | 70.3% | — |
| NYT Connections (extended) | — | 79.2% |
| CritPt | — | 17.7% |
| LMArena Hard Prompts | — | 1486 |
| DTBench | — | 94.7% |
| LMCA | — | 48.4% |
| Epoch Capabilities Index | — | 154.87 |

## Math

- GPT-5-Codex: —
- Muse Spark 1.2: 46.4 (#70)

| Benchmark | GPT-5-Codex | Muse Spark 1.2 |
|---|---|---|
| ProofBench | — | 43% |
| LMArena Math | — | 1471 |

## Knowledge

- GPT-5-Codex: —
- Muse Spark 1.2: 54.1 (#53)

| Benchmark | GPT-5-Codex | Muse Spark 1.2 |
|---|---|---|
| SimpleQA Verified | — | 60.3% |
| LMArena Expert | — | 1480 |

## Multimodal

- GPT-5-Codex: —
- Muse Spark 1.2: 43.4 (#25)

| Benchmark | GPT-5-Codex | Muse Spark 1.2 |
|---|---|---|
| LMArena Vision | — | 1305 |

## Multilingual

- GPT-5-Codex: —
- Muse Spark 1.2: 57.1 (#11)

| Benchmark | GPT-5-Codex | Muse Spark 1.2 |
|---|---|---|
| LMArena Non-English | — | 1478 |
| LMArena Chinese | — | 1511 |
| LMArena French | — | 1513 |
| LMArena Russian | — | 1487 |
| LMArena Spanish | — | 1498 |

## Instruction Following

- GPT-5-Codex: —
- Muse Spark 1.2: 76.7 (#36)

| Benchmark | GPT-5-Codex | Muse Spark 1.2 |
|---|---|---|
| LMArena Instruction Following | — | 1461 |

## Long Context

- GPT-5-Codex: —
- Muse Spark 1.2: 45.2 (#48)

| Benchmark | GPT-5-Codex | Muse Spark 1.2 |
|---|---|---|
| LMArena Longer Query | — | 1475 |

## Writing & Preference

- GPT-5-Codex: —
- Muse Spark 1.2: 72.3 (#14)

| Benchmark | GPT-5-Codex | Muse Spark 1.2 |
|---|---|---|
| LMArena Text | — | 1482 |
| LMArena Creative Writing | — | 1449 |
| EQ-Bench Creative Writing | — | 1840 |
| LMArena Multi-Turn | — | 1494 |

## FAQ

### Is GPT-5-Codex better than Muse Spark 1.2?

Muse Spark 1.2 is the stronger model overall, scoring 50.3 to 37.9 on the Noometry Index.

### Which is cheaper, GPT-5-Codex or Muse Spark 1.2?

Muse Spark 1.2 is cheaper. It lists at $1.25 per million input tokens and $4.25 per million output tokens; GPT-5-Codex lists at $1.25 and $10.

### Is GPT-5-Codex or Muse Spark 1.2 better for coding?

Muse Spark 1.2 scores higher on coding benchmarks: 49.2 versus 42.4 in the Noometry coding category.

### Which has the bigger context window?

Muse Spark 1.2 does, with 1.05M tokens against 400K.

### How many benchmarks do GPT-5-Codex and Muse Spark 1.2 share?

1 benchmark has published results for both models. GPT-5-Codex has 3 scored results on Noometry and Muse Spark 1.2 has 31.