Coding work
Code generation, repair, and software-engineering tasks
GPT-5.2
GPT-5.2 has the higher public coding point estimate, 59.2 to 57.6, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Updated November 21, 2026. Rank says GPT-5.2 is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
GPT-5.2 has the higher public score estimate, 60.2 versus 59.2, but the 90% score intervals overlap. Treat that as a lead, not a settled winner. 9 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
GPT-5.2: $1.75 input / $14 output
Muse Spark 1.1: No comparable API price
GPT-5.2: 400K
Muse Spark 1.1: 1M
GPT-5.2: December 11, 2025
Muse Spark 1.1: July 9, 2026
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.
Code generation, repair, and software-engineering tasks
GPT-5.2
GPT-5.2 has the higher public coding point estimate, 59.2 to 57.6, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Prompts that approach the documented context limit
Muse Spark 1.1
Muse Spark 1.1 has the larger documented context window.
Tool use, computer use, and multi-step task completion
No clear pick
The like-for-like agentic result is a practical tie on the public lane (within 0.5 points).
1K fresh input + 500 output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
200K cached + 20K fresh input + 10K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
50K fresh input + 3K output tokens
Not enough matched evidence
A complete comparable API-rate estimate is not available for both models.
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.
Like-for-like · BenchAlign v6.0
GPT-5.2 has the higher coding point estimate. Conditional score ranges do not establish rank confidence.
Coding scores combine specific tasks and setups. Match the editor, harness, and effort to your workflow.
The LLM Selector reads what you need a model for and returns a shortlist, ranked in the same order the job pages publish.
We keep what you type here, drafts included, for 180 days, and after that only the job and requirements read from it. Nothing is tied to your IP address or account. Leave out names and other personal details. Privacy
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
3 categories rest on Estimated evidence or different evidence sets. Those rows remain visible for coverage context but do not name a winner.
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.
OSWorld-VerifiedAgentic
Normalized gap 33.5CharXivMultimodal
Normalized gap 6.3SWE-bench ProCoding
Normalized gap 5.9MMLU-Pro (Vals)Knowledge
Normalized gap 2.5LiveCodeBench (Vals)Coding
Normalized gap 0.5Each row shows the public-lane category score for both models: the BenchAlign v6.0 lane in every category, with the same rank each model page reports. A row is like-for-like only when both scores rest on Supported evidence. Directional and not-comparable rows remain visible, but they never receive a winner.
| Category | GPT-5.2 | Muse Spark 1.1 | Basis | Reading |
|---|---|---|---|---|
| Agentic | 59.9Supported · #58/182 | 59.9Supported · #57/182 | Like-for-likeBenchAlign v6.0 lane · 5 vs 15 public rows | Tie |
| Coding | 59.2Supported · #59/180 | 57.6Supported · #63/180 | Like-for-likeBenchAlign v6.0 lane · 6 vs 4 public rows | GPT-5.2 leads · intervals overlap |
| Reasoning | 59.9Supported · #47/161 | 57.2Supported · #53/161 | Like-for-likeBenchAlign v6.0 lane · 3 vs 1 public rows | GPT-5.2 leads · intervals overlap |
| Instruction following | 54.6Supported · #52/143 | 56.9Supported · #44/143 | Like-for-likeBenchAlign v6.0 lane · 0 vs 0 public rows | Muse Spark 1.1 leads · intervals overlap |
| Multimodal | 51.9Estimated · #68/119 | 58.9Estimated · #53/119 | Directional onlyBenchAlign v6.0 lane · 18 vs 2 public rows | Directional only |
| Knowledge | 60.7Supported · #40/158 | 55.4Estimated · #63/158 | Directional onlyBenchAlign v6.0 lane · 3 vs 5 public rows | Directional only |
| Math | 59.5Supported · #33/125 | 55.2Estimated · #50/125 | Directional onlyBenchAlign v6.0 lane · 3 vs 0 public rows | Directional only |
| Multilingual | Not ranked | Not ranked | Not comparableBenchAlign v6.0 lane · 0 vs 0 public rows | Not comparable |
Ranks count the models scored in each category’s BenchAlign v6.0 lane, so denominators differ by category. Like-for-like rows within 0.5 points read as a practical tie.
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.
1K fresh input + 500 output tokens
Muse Spark 1.1 has no comparable published API token rate.
50K fresh input + 3K output tokens
Muse Spark 1.1 has no comparable published API token rate.
200K cached + 20K fresh input + 10K output tokens
GPT-5.2 has no published cached-input rate, so cached tokens use its listed input rate. Muse Spark 1.1 has no comparable published API token rate.
Overall score against output price per 1M tokens, one model per family. Pricing as of November 21, 2026.
GPT-5.2
Gray dots are the other priced models. The dark step line is the efficiency frontier: for a model under it, another model costs no more and scores at least as high.
See GPT-5.2 on the full price vs performance chartSourced differences are shown directly. Missing facts stay explicit instead of being inferred from a model name or family.
Maximum documented context; output-token limits may be lower.
GPT-5.2
400K
Muse Spark 1.1
1M
GPT-5.2
Not sourced
Muse Spark 1.1
Not sourced
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
GPT-5.2
Not published
Muse Spark 1.1
No comparable hosted API rate
GPT-5.2
text, image
OpenAI model page for gpt-5.2Muse Spark 1.1
text, image, video, document
Meta Muse Spark 1.1 model pageGPT-5.2
Muse Spark 1.1
GPT-5.2
Not sourced
Muse Spark 1.1
Not sourced
GPT-5.2
Reasoning
Muse Spark 1.1
Reasoning
GPT-5.2
Proprietary
Muse Spark 1.1
Proprietary
GPT-5.2
Proprietary
Muse Spark 1.1
Proprietary
GPT-5.2
2025-12-11
Muse Spark 1.1
2026-07-09
GPT-5.2 has the higher public score estimate, 60.2 versus 59.2, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
GPT-5.2 has the higher public coding point estimate, 59.2 to 57.6, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
The like-for-like agentic tasks row is tied on the public lane, 59.9 each.
Both models do not have comparable published API token rates, so this page does not name a universal price winner.
Muse Spark 1.1 has the larger documented context window: 1M, compared with 400K.
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
LifeVal
Not directly comparable
BrowseComp
Not directly comparable
OSWorld-Verified
Muse Spark 1.1 leads this result
Gert Labs
Shared sourceMuse Spark 1.1 leads this result
JobBench
Muse Spark 1.1 leads this result
Terminal-Bench 2.1
Not directly comparable
MCP Atlas
Not directly comparable
Toolathlon
Not directly comparable
WebArena-Verified
Not directly comparable
DeepSearchQA
Not directly comparable
CyberGym
Not directly comparable
Finance Agent v2
Not directly comparable
deepSwe
Not directly comparable
OSWorld 2.0
Not directly comparable
Cybench
Not directly comparable
ExploitGym
Not directly comparable
Terminal-Bench 2.1 (Vals)
Not directly comparable
SWE-bench Verified
Not directly comparable
SWE-bench Pro
Muse Spark 1.1 leads this result
Vibe Code Bench
Not directly comparable
LiveCodeBench (Vals)
Muse Spark 1.1 leads this result
SWE-bench (Vals)
Muse Spark 1.1 leads this result
PostTrainBench v1
Not directly comparable
Terminal-Bench 2.1
Not directly comparable
MMMU
Not directly comparable
MMMU-Pro
Not directly comparable
RealWorldQA
Not directly comparable
OmniDocBench 1.5
Not directly comparable
Video-MME (with subtitle)
Not directly comparable
Video-MME (w/o subtitle)
Not directly comparable
MathVision
Not directly comparable
We-Math
Not directly comparable
DynaMath
Not directly comparable
SimpleVQA
Not directly comparable
CC-OCR
Not directly comparable
AI2D_TEST
Not directly comparable
CountBench
Not directly comparable
ERQA
Not directly comparable
VideoMMMU
Not directly comparable
MLVU (M-Avg)
Not directly comparable
CharXiv
Muse Spark 1.1 leads this result
V*
Not directly comparable
BabyVision
Not directly comparable
GPQA
Not directly comparable
GPQA Diamond (Vals)
GPT-5.2 leads this result
MMLU-Pro (Vals)
Muse Spark 1.1 leads this result
HLE
Not directly comparable
HLE w/o tools
Not directly comparable
HealthBench Professional
Not directly comparable
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 7,000+ subscribers.
Last updated November 21, 2026