Updated October 29, 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, 59.41 versus 49.5, but the 90% score intervals overlap. Treat that as a lead, not a settled winner. 10 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
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.
Tool use, computer use, and multi-step task completion
GPT-5.2
GPT-5.2 has the higher public agentic point estimate, 45.5 to 36.1, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Prompts that approach the documented context limit
Inkling-Small
Inkling-Small has the larger documented context window.
1K fresh input + 500 output tokens
Inkling-Small
Inkling-Small has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
Inkling-Small
Inkling-Small has the lower estimated token cost for this stated workload. GPT-5.2 has no published cached-input rate, so cached tokens use its listed input rate.
50K fresh input + 3K output tokens
Inkling-Small
Inkling-Small has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
Code generation, repair, and software-engineering tasks
No clear pick
The like-for-like coding result is a practical tie on the public lane (within 0.5 points).
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 v5.8
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.
Shared results can support a head-to-head reading. Results present for only one model describe coverage, not superiority.
1 category rests 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.
FrontierMath v2 (Tiers 1-3)Math
Normalized gap 21.1FrontierMath v2 (Tier 4)Math
Normalized gap 14.6ARC-AGI-2Reasoning
Normalized gap 12.8BrowseCompAgentic
Normalized gap 11.6MMMU-ProMultimodal
Normalized gap 5.5Each row shows the public-lane category score for both models: the BenchAlign v5.8 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.
| Category | GPT-5.2 | Inkling-Small | Basis | Reading |
|---|---|---|---|---|
| Agentic | 45.5Supported · #63/135 | 36.1Supported · #86/135 | Like-for-likeBenchAlign v5.8 lane · 4 vs 5 public rows | GPT-5.2 leads · intervals overlap |
| Coding | 37.0Supported · #76/156 | 36.9Supported · #77/156 | Like-for-likeBenchAlign v5.8 lane · 3 vs 6 public rows | Practical tie |
| Multimodal | 75.5#25/58 | 67.3#41/58 | Like-for-likeProvisional lane · 2 vs 2 weighted rows | GPT-5.2 leads |
| Knowledge | 59.1Supported · #50/179 | 50.6Supported · #75/179 | Like-for-likeBenchAlign v5.8 lane · 1 vs 6 public rows | GPT-5.2 leads · intervals overlap |
| Instruction following | 92.6#20/157 | 93.3#10/157 | Directional onlyProvisional lane · 0 vs 1 weighted rows | Directional only |
| Reasoning | 64.3Unranked · 4 rankable rows | 55.0Unranked · 4 rankable rows | Not comparableProvisional lane · 1 vs 1 weighted rows | Not comparable |
| Multilingual | Not ranked | Not ranked | Not comparableProvisional lane · 0 vs 0 weighted rows | Not comparable |
| Math | 71.1Unranked · 3 rankable rows | 69.8#5/12 | Not comparableProvisional lane · 2 vs 4 weighted rows | Not comparable |
Ranks count the models scored in each category’s lane, so the agentic, coding, and knowledge denominators (BenchAlign v5.8) differ from the provisional-lane categories. Unranked scores sit on the provisional lane’s scale but never name a winner. 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
Inkling-Small has the lower modeled cost
Costs use the listed standard API rates.
50K fresh input + 3K output tokens
Inkling-Small has the lower modeled cost
Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
Inkling-Small has the lower modeled cost
GPT-5.2 has no published cached-input rate, so cached tokens use its listed input rate.
Sourced 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
Inkling-Small
1M
GPT-5.2
Not sourced
Inkling-Small
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
Inkling-Small
$0.116 per 1M cached input tokens
GPT-5.2
Not sourced
Inkling-Small
Not sourced
GPT-5.2
Not sourced
Inkling-Small
Not sourced
GPT-5.2
Not sourced
Inkling-Small
Not sourced
GPT-5.2
Reasoning
Inkling-Small
Hybrid
GPT-5.2
Proprietary
Inkling-Small
Open Weight
GPT-5.2
Proprietary
Inkling-Small
Open Weight
GPT-5.2
2025-12-11
Inkling-Small
2026-07-30
GPT-5.2 has the higher public score estimate, 59.41 versus 49.5, but the 90% score intervals overlap. The higher estimate is not a decisive winner because the uncertainty ranges overlap.
The like-for-like coding row is a practical tie on the public lane, 37 against 36.9, inside the 0.5-point band BenchLM treats as level.
GPT-5.2 has the higher public agentic tasks point estimate, 45.5 to 36.1, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
For the stated presets, chat costs $0.00875 on GPT-5.2 and $0.0013 on Inkling-Small; repository review costs $0.1295 and $0.03332; the cache-heavy agent loop costs $0.525 and $0.0492. GPT-5.2 has no published cached-input rate, so cached tokens use its listed input rate.
Inkling-Small 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.
BrowseComp
Inkling-Small leads this result
OSWorld-Verified
Not directly comparable
Gert Labs
Not directly comparable
JobBench
Not directly comparable
Terminal-Bench 2.1
Not directly comparable
MCP Atlas
Not directly comparable
Toolathlon-Verified
Not directly comparable
Terminal-Bench 2.1 (Vals)
Not directly comparable
SWE-bench Verified
Inkling-Small leads this result
SWE-bench Pro
Inkling-Small leads this result
Vibe Code Bench
Not directly comparable
Terminal-Bench 2.1
Not directly comparable
SciCode
Not directly comparable
LiveCodeBench (Vals)
Not directly comparable
SWE-bench (Vals)
Not directly comparable
MMMU
Not directly comparable
MMMU-Pro
GPT-5.2 leads this result
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
GPT-5.2 leads this result
V*
Not directly comparable
CharXiv w/o tools
Not directly comparable
GPQA
GPT-5.2 leads this result
GPQA-D
Not directly comparable
HLE
Not directly comparable
HLE w/o tools
Not directly comparable
GPQA Diamond (Vals)
Not directly comparable
MMLU-Pro (Vals)
Not directly comparable
IFBench
Not directly comparable
AIME 2025
Not directly comparable
FrontierMath v2 (Tiers 1-3)
Shared sourceGPT-5.2 leads this result
FrontierMath v2 (Tier 4)
Shared sourceGPT-5.2 leads this result
AIME26
Not directly comparable
HMMT Feb 2026
Not directly comparable
One weekly email when material rank, price, or benchmark evidence changes make this matchup worth revisiting.
Read a sample issueJoin 6,100+ subscribers.
Last updated October 29, 2026
