Coding
Like-for-like- GPT-5.4 mini
- 42.6
- Supported · #106/154
- Muse Spark 1.2
- 60.0
- Supported · #21/154
- Basis
- BenchAlign lane · 4 vs 5 public rows
- Reading
- Muse Spark 1.2 leads · intervals overlap
GPT-5.4 mini vs Muse Spark 1.2
Decision reading
Muse Spark 1.2 has the higher public score estimate, 70.28 versus 61.05, but the 90% score intervals overlap. Treat that as a lead, not a settled winner.
3 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Updated September 18, 2026. Rank says Muse Spark 1.2 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
Both of these models will change. Get the price, version and retirement notices for the pair, each with its source. Follow model changes
Share or export
Which one for your work
Recommendations appear only when a shared evidence basis or an explicit operating constraint supports the call. Secondary and unsupported use cases stay disclosed below the initial list.
Coding work
Code generation, repair, and software-engineering tasks
Muse Spark 1.2
Muse Spark 1.2 leads on the public coding lane, 60 to 42.6, with Supported evidence for both models, although the 90% intervals overlap.
Confidence: limited
Long documents
Prompts that approach the documented context limit
Muse Spark 1.2
Muse Spark 1.2 has the larger documented context window.
Confidence: documented
Chat turn cost
1K fresh input + 500 output tokens
GPT-5.4 mini
GPT-5.4 mini has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Show secondary and unsupported calls
Cache-heavy agent loop cost
200K cached + 20K fresh input + 10K output tokens
GPT-5.4 mini
GPT-5.4 mini has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Repository review cost
50K fresh input + 3K output tokens
GPT-5.4 mini
GPT-5.4 mini has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Confidence: listed-rates
Agentic work
Tool use, computer use, and multi-step task completion
Not enough matched evidence
GPT-5.4 mini is scored on Estimated evidence for agentic, so the reading is directional rather than like-for-like.
Confidence: limited
Which one for a specific job
Choose a job from the LLM Selector's task catalog to see the category row it rests on, under the same basis rules as the table below. A directional row stays directional; choosing a job never creates a winner.
The same task catalog as the LLM Selector. Each job names the evidence surface it rests on; nothing here adds a new score.
42.6GPT-5.4 mini60.0Muse Spark 1.2
Like-for-like · BenchAlign
Muse Spark 1.2 leads the like-for-like coding row, although the 90% intervals overlap.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
What is actually comparable
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
16 GPT-5.4 mini only
3 Shared
5 Muse Spark 1.2 only
- Shared results
- 3
- GPT-5.4 mini only
- 16
- Muse Spark 1.2 only
- 5
- Like-for-like categories
- 1 / 8
2 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
Category results, on a stated basis
Each row shows the public-lane category score for both models: the BenchAlign lane for agentic, coding, and knowledge, and the weighted public rows elsewhere, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence or the same weighted set. Directional and not-comparable rows remain visible, but they never receive a winner.
Agentic
Directional only- GPT-5.4 mini
- 39.1
- Estimated · #124/154
- Muse Spark 1.2
- 61.0
- Supported · #16/154
- Basis
- BenchAlign lane · 6 vs 2 public rows
- Reading
- Directional only
Knowledge
Directional only- GPT-5.4 mini
- 55.6
- Supported · #52/184
- Muse Spark 1.2
- 70.7
- Estimated · #10/184
- Basis
- BenchAlign lane · 5 vs 1 public rows
- Reading
- Directional only
Reasoning
Not comparable- GPT-5.4 mini
- 73.9
- Unranked · 2 rankable rows
- Muse Spark 1.2
- 75.3
- Unranked · 2 rankable rows
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Math
Not comparable- GPT-5.4 mini
- 44.3
- Unranked · 2 rankable rows
- Muse Spark 1.2
- Not ranked
- Basis
- Provisional lane · 2 vs 0 weighted rows
- Reading
- Not comparable
Multilingual
Not comparable- GPT-5.4 mini
- Not ranked
- Muse Spark 1.2
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
Multimodal
Not comparable- GPT-5.4 mini
- 57.3
- #31/48
- Muse Spark 1.2
- Not ranked
- Basis
- Provisional lane · 1 vs 0 weighted rows
- Reading
- Not comparable
Instruction following
Not comparable- GPT-5.4 mini
- 88.5
- #24/124
- Muse Spark 1.2
- Not ranked
- Basis
- Provisional lane · 0 vs 0 weighted rows
- Reading
- Not comparable
| Category | GPT-5.4 mini | Muse Spark 1.2 | Basis | Reading |
|---|---|---|---|---|
| Coding | 42.6Supported · #106/154 | 60.0Supported · #21/154 | Like-for-likeBenchAlign lane · 4 vs 5 public rows | Muse Spark 1.2 leads · intervals overlap |
| Agentic | 39.1Estimated · #124/154 | 61.0Supported · #16/154 | Directional onlyBenchAlign lane · 6 vs 2 public rows | Directional only |
| Knowledge | 55.6Supported · #52/184 | 70.7Estimated · #10/184 | Directional onlyBenchAlign lane · 5 vs 1 public rows | Directional only |
| Reasoning | 73.9Unranked · 2 rankable rows | 75.3Unranked · 2 rankable rows | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 44.3Unranked · 2 rankable rows | Not ranked | Not comparableProvisional lane · 2 vs 0 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Multimodal | 57.3#31/48 | Not ranked | Not comparableProvisional lane · 1 vs 0 weighted rows | Not comparable |
| Instruction following | 88.5#24/124 | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign) differ from the provisional-lane categories. Unranked scores sit on the lane’s scale but never name a winner. Like-for-like rows within 0.5 points read as a practical tie.
Shape of the matched evidence
Only shared public evidence is shown. Sparse evidence stays a ruled list rather than being closed into a radar shape.
Too few matched category axes support a radar. The ruled list below shows only shared benchmark results; positions use each benchmark’s normalized display scale when available.
MMLU-Pro (Vals)
Knowledge
What each workload costs
Three fixed token mixes turn per-token rates into comparable decisions. Each scenario states context fit and whether cached input had to fall back to the published list-input rate.
Chat turn
1K fresh input + 500 output tokens
- GPT-5.4 mini
- $0.003
- Fits in one request
- Muse Spark 1.2
- $0.00338
- Fits in one request
GPT-5.4 mini has the lower modeled cost
Costs use the listed standard API rates.
Repository review
50K fresh input + 3K output tokens
- GPT-5.4 mini
- $0.051
- Fits in one request
- Muse Spark 1.2
- $0.07525
- Fits in one request
GPT-5.4 mini has the lower modeled cost
Costs use the listed standard API rates.
Cache-heavy agent loop
200K cached + 20K fresh input + 10K output tokens
- GPT-5.4 mini
- $0.075
- Fits in one request
- Muse Spark 1.2
- $0.0975
- Fits in one request
GPT-5.4 mini has the lower modeled cost
Costs use the listed standard API rates.
Specification differences
Sourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
SpecificationGPT-5.4 miniMuse Spark 1.2
Context window
Maximum documented context; output-token limits may be lower.
GPT-5.4 mini
Muse Spark 1.2
API model ID
GPT-5.4 mini
gpt-5.4-mini
OpenAI GPT-5.4 mini model documentationMuse Spark 1.2
muse-spark-1.2
Meta: Muse Spark 1.2 model pageCached-input rate
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
GPT-5.4 mini
$0.075 per 1M cached input tokens
OpenAI pricingMuse Spark 1.2
$0.15 per 1M cached input tokens
Meta: Muse Spark 1.2 model pageDocumented inputs
GPT-5.4 mini
text, image
OpenAI model catalogMuse Spark 1.2
Not sourced
Documented outputs
GPT-5.4 mini
Muse Spark 1.2
Not sourced
Provider availability
GPT-5.4 mini
Generally Available · OpenAI Responses API
OpenAI model catalogMuse Spark 1.2
Not sourced
Reasoning profile
GPT-5.4 mini
Reasoning
Muse Spark 1.2
Reasoning
Weight access
GPT-5.4 mini
Proprietary
Muse Spark 1.2
Proprietary
License
GPT-5.4 mini
Proprietary
Muse Spark 1.2
Proprietary
Release date
GPT-5.4 mini
2026-03-17
Muse Spark 1.2
2026-08-05
If you already use one of these models
- Deployment change
- The models list different providers, so authentication, endpoint behavior, limits, and feature support may change.
- Quality signal
- Muse Spark 1.2 has the higher public score estimate, 70.28 versus 61.05, but the 90% score intervals overlap.
- Workload cost
- Repository review: $0.051 vs $0.07525. Cache-heavy agent loop: $0.075 vs $0.0975.
- Context tradeoff
- Muse Spark 1.2 has the larger documented window (1M).
Run the same representative tasks against both endpoints before changing production traffic.
Benchmark evidence
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Browse raw public benchmark evidence24 rows
Agentic
Terminal-Bench 2.0
GPT-5.4 mini60%SourceMuse Spark 1.2—Not directly comparable
OSWorld-Verified
GPT-5.4 mini72.1%SourceMuse Spark 1.2—Not directly comparable
MCP Atlas
GPT-5.4 mini57.7%SourceMuse Spark 1.2—Not directly comparable
Toolathlon
GPT-5.4 mini42.9%SourceMuse Spark 1.2—Not directly comparable
τ²-bench results
GPT-5.4 mini93.4%SourceMuse Spark 1.2—Not directly comparable
Terminal-Bench 2.1 (Vals)
GPT-5.4 mini54.7%SourceMuse Spark 1.269.7%SourceMuse Spark 1.2 leads this result
Terminal-Bench 2.1
GPT-5.4 mini—Muse Spark 1.282.9%SourceNot directly comparable
Coding
Vibe Code Bench
GPT-5.4 mini47.97%SourceMuse Spark 1.2—Not directly comparable
FrontierCode 1.1 Main
GPT-5.4 mini27.0%SourceMuse Spark 1.2—Not directly comparable
LiveCodeBench (Vals)
GPT-5.4 mini81.5%SourceMuse Spark 1.2—Not directly comparable
SWE-bench (Vals)
GPT-5.4 mini73.0%SourceMuse Spark 1.286.6%SourceMuse Spark 1.2 leads this result
Terminal-Bench 2.1
GPT-5.4 mini—Muse Spark 1.282.9%SourceNot directly comparable
DeepSWE
GPT-5.4 mini—Muse Spark 1.259.3%SourceNot directly comparable
VulcanBench v3
GPT-5.4 mini—Muse Spark 1.287.0%SourceNot directly comparable
FrontierSWE v2
GPT-5.4 mini—Muse Spark 1.212.0%SourceNot directly comparable
Knowledge
GPQA
GPT-5.4 mini88%SourceMuse Spark 1.2—Not directly comparable
HLE
GPT-5.4 mini41.5%SourceMuse Spark 1.2—Not directly comparable
HLE w/o tools
GPT-5.4 mini28.2%SourceMuse Spark 1.2—Not directly comparable
GPQA Diamond (Vals)
GPT-5.4 mini83.1%SourceMuse Spark 1.2—Not directly comparable
MMLU-Pro (Vals)
GPT-5.4 mini84.6%SourceMuse Spark 1.288.3%SourceMuse Spark 1.2 leads this result
Math
Multimodal
Questions
Which is better, GPT-5.4 mini or Muse Spark 1.2?
Muse Spark 1.2 has the higher public score estimate, 70.28 versus 61.05, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
Which is better for coding, GPT-5.4 mini or Muse Spark 1.2?
Muse Spark 1.2 leads the public coding lane, 60 to 42.6, with Supported evidence for both models, although the 90% intervals overlap.
Which is better for agentic tasks, GPT-5.4 mini or Muse Spark 1.2?
Muse Spark 1.2 scores higher for agentic tasks on the public lane, 61 to 39.1. GPT-5.4 mini is scored on Estimated evidence for agentic tasks, so the reading is directional rather than like-for-like. BenchLM does not name a winner for agentic tasks from a directional reading; read the shared benchmark rows directly and test the models on the same task set.
Which costs less, GPT-5.4 mini or Muse Spark 1.2?
For the stated presets, chat costs $0.003 on GPT-5.4 mini and $0.00337 on Muse Spark 1.2; repository review costs $0.051 and $0.07525; the cache-heavy agent loop costs $0.075 and $0.0975. Costs use the listed standard API rates.
Which has the larger context window, GPT-5.4 mini or Muse Spark 1.2?
Muse Spark 1.2 has the larger documented context window: 1M, compared with 400K.
Related comparisons
Last updated September 18, 2026
Watch GPT-5.4 mini vs Muse Spark 1.2
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 2,000+ readers.