- Score
- 9.4 (+0.46 points)
- Total Cost (Current Price)
- $0.183 · 91.0% cheaper
- Response Time (avg)
- 6.24s · 77.8% faster
Meta
Release: 2026-08-06
Tested on: 2026-10-01 03:06
meta/muse-spark-1.2::high
~1T total (~50B active)MoEClosedEstimated
Summary
Muse Spark 1.2 scores 8.9 on AI BENCHY and ranks #60. It has 9.9 reliability, a 75.4% pass rate, $2.018 total cost, and 28.15s average response time.
What makes Muse Spark 1.2 unique: It uses unusually many reasoning tokens, which can help explain its slower or more expensive runs.
Recommended alternatives
We recommend choosing one of these models instead:
- Score
- 9.1 (+0.22 points)
- Total Cost (Current Price)
- $0.140 · 93.1% cheaper
- Response Time (avg)
- 16.58s · 41.1% faster
- Score
- 9.6 (+0.65 points)
- Total Cost (Current Price)
- $0.460 · 77.2% cheaper
- Response Time (avg)
- 7.15s · 74.6% faster
Model facts
Researched on 2026-08-12
- Parameters
- ~1T total (~50B active)
- Architecture
- MoE
- Availability
- Closed
- License
- -
Best estimate from public evidence; the vendor did not disclose every value. API-only exact checkpoint; promised weights were not public at research time.
8.9
Consistency
8.4
9.9
$2.018
Total Output Tokens
392,846
Total Input Tokens
277,967
Input Price
$1.250 / 1M
Output Price
$4.250 / 1M
Cache Read Price
$0.150 / 1M
Cache Write Price
N/A
Cache prices apply to input tokens. Reads reuse cached prompts; writes store them and can cost extra. Output tokens use the output price.
Flaky tests
5
Flaky tests had mixed outcomes across runs (at least one pass and one fail).
Hamster playing table tennis
Prompt: Create a detailed SVG illustration of a hamster playing table tennis.
#60 Muse Spark 1.2
high- Cost
- $0.057
- Time
- 34.7s
- Tokens
- 13,356 tok
Run history
| Tested on | Score | Reliability | Tests Correct | Total Cost | Compare |
|---|---|---|---|---|---|
| 2026-10-01 03:06 Re-test | 8.9 | 9.9 | $2.018 | Current run | |
| 2026-08-05 23:33 Initial run | 8.8 | 9.8 | $1.632 | Compare |
This run used a different benchmark suite. Keep suite changes in mind when reading historical movement.
Price History
Historical pricing data for this model from OpenRouter.
| Date | Input Price | Output Price | Cache Read Price | Cache Write Price |
|---|---|---|---|---|
| 2026-08-14 12:51 | $1.250 / 1M | $4.250 / 1M | N/A | N/A |
| 2026-10-01 18:33 | $1.250 / 1M | $4.250 / 1M | $0.150 / 1M | N/A |
Charts
Choose the first model, then click a second model to open a side-by-side page.
Top Models by Score
Score vs Total Cost
Response Time (avg)
Score vs Response Time (avg)
Total Output Tokens
Score vs Total Output Tokens
Quick Compare
Muse Spark 1.2highvsMuse Spark OpenlowMuse Spark 1.2highvsMuse Spark 1.2mediumMuse Spark 1.2highvsGLM 5.3 FlashmaxMuse Spark 1.2highvsMuse Spark 1.1mediumMuse Spark 1.2highvsGemini 3.6 FlashlowMuse Spark 1.2highvsClaude Fable 5mediumMuse Spark 1.2highvsClaude Opus 5lowMuse Spark 1.2highvsPareto 26.9defaultMuse Spark 1.2highvsGemini 4 ArgonmediumMuse Spark 1.2highvsKimi K3.1 Prolow
Category Breakdown
| Category | Score | Consistency | Tests Correct |
|---|---|---|---|
| Agentic | 10.0 | 10.0 | |
| Anti-AI Tricks | 7.1 | 8.4 | |
| Coding | 10.0 | 10.0 | |
| Combined | 8.0 | 6.9 | |
| Data parsing and extraction | 10.0 | 10.0 | |
| Domain specific | 4.1 | 4.4 | |
| General Intelligence | 10.0 | 10.0 | |
| Instructions following | 9.8 | 10.0 | |
| Puzzle Solving | 8.2 | 7.7 | |
| Tool Calling | 10.0 | 10.0 | |
| Trivia | 3.0 | 10.0 |