Coding work
Code generation, repair, and software-engineering tasks
GPT-5.6 Sol
GPT-5.6 Sol has the higher public coding point estimate, 74.2 to 60.5, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Updated November 21, 2026. Rank says GPT-5.6 Sol is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
GPT-5.6 Sol has the higher public score, 73.2 versus 60.4, and the 90% score intervals do not overlap. 20 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
GPT-5.6 Sol: $4 input / $20 output
Grok 4.5: $2 input / $6 output
GPT-5.6 Sol: 1.05M
Grok 4.5: 500K
GPT-5.6 Sol: July 9, 2026
Grok 4.5: July 8, 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-5.6 Sol
GPT-5.6 Sol has the higher public coding point estimate, 74.2 to 60.5, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Tool use, computer use, and multi-step task completion
GPT-5.6 Sol
GPT-5.6 Sol has the higher public agentic point estimate, 72.8 to 57.8, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Prompts that approach the documented context limit
GPT-5.6 Sol
GPT-5.6 Sol has the larger documented context window.
1K fresh input + 500 output tokens
Grok 4.5
Grok 4.5 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
Grok 4.5
Grok 4.5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
50K fresh input + 3K output tokens
Grok 4.5
Grok 4.5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
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-5.6 Sol 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.
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 (Tier 4)Math
Normalized gap 58.6ARC-AGI-2Reasoning
Normalized gap 39.9FrontierMath v2 (Tiers 1-3)Math
Normalized gap 31.8ARC-AGI-3Reasoning
Normalized gap 7.5LiveCodeBench (Vals)Coding
Normalized gap 4.8Each 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-5.6 Sol | Grok 4.5 | Basis | Reading |
|---|---|---|---|---|
| Agentic | 72.8Supported · #18/182 | 57.8Supported · #65/182 | Like-for-likeBenchAlign v6.0 lane · 13 vs 6 public rows | GPT-5.6 Sol leads |
| Coding | 74.2Supported · #21/180 | 60.5Supported · #54/180 | Like-for-likeBenchAlign v6.0 lane · 17 vs 9 public rows | GPT-5.6 Sol leads · intervals overlap |
| Reasoning | 73.0Supported · #18/161 | 59.9Supported · #48/161 | Like-for-likeBenchAlign v6.0 lane · 5 vs 3 public rows | GPT-5.6 Sol leads · intervals overlap |
| Multimodal | 71.7Supported · #15/119 | 62.9Supported · #43/119 | Like-for-likeBenchAlign v6.0 lane · 4 vs 0 public rows | GPT-5.6 Sol leads · intervals overlap |
| Knowledge | 71.9Supported · #14/158 | 61.3Supported · #39/158 | Like-for-likeBenchAlign v6.0 lane · 8 vs 2 public rows | GPT-5.6 Sol leads · intervals overlap |
| Instruction following | 67.0Supported · #19/143 | 57.7Supported · #40/143 | Like-for-likeBenchAlign v6.0 lane · 1 vs 0 public rows | GPT-5.6 Sol leads · intervals overlap |
| Math | 71.9Supported · #16/125 | 57.5Supported · #42/125 | Like-for-likeBenchAlign v6.0 lane · 3 vs 2 public rows | GPT-5.6 Sol leads · intervals overlap |
| Multilingual | 68.0Estimated · #10/88 | 59.0Estimated · #27/88 | Directional onlyBenchAlign v6.0 lane · 0 vs 0 public rows | Directional only |
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
Grok 4.5 has the lower modeled cost
Costs use the listed standard API rates.
50K fresh input + 3K output tokens
Grok 4.5 has the lower modeled cost
Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
Grok 4.5 has the lower modeled cost
Costs use the listed standard API rates.
Enter a month of tokens to price it at both models’ listed API rates.
Standard listed rates, no batch or volume discounts.
Overall score against output price per 1M tokens, one model per family. Pricing as of November 21, 2026.
GPT-5.6 SolGrok 4.5
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 Grok 4.5 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-5.6 Sol
1.05M
OpenAI model catalogGrok 4.5
500K
GPT-5.6 Sol
gpt-5.6-sol
OpenAI model catalogGrok 4.5
Not sourced
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
GPT-5.6 Sol
$0.4 per 1M cached input tokens
OpenAI pricingGrok 4.5
$0.3 per 1M cached input tokens
GPT-5.6 Sol
text, image
OpenAI model catalogGrok 4.5
text, image
xAI model page for grok-4.5GPT-5.6 Sol
Grok 4.5
GPT-5.6 Sol
Generally Available · OpenAI Responses API
OpenAI model catalogGrok 4.5
Not sourced
GPT-5.6 Sol
Reasoning
Grok 4.5
Reasoning
GPT-5.6 Sol
Proprietary
Grok 4.5
Proprietary
GPT-5.6 Sol
Proprietary
Grok 4.5
Proprietary
GPT-5.6 Sol
2026-07-09
Grok 4.5
2026-07-08
GPT-5.6 Sol has the higher public score, 73.2 versus 60.4, and the 90% score intervals do not overlap. That is the clearest overall quality signal in the current public data.
GPT-5.6 Sol has the higher public coding point estimate, 74.2 to 60.5, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
GPT-5.6 Sol has the higher public agentic tasks point estimate, 72.8 to 57.8, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
For the stated presets, chat costs $0.014 on GPT-5.6 Sol and $0.005 on Grok 4.5; repository review costs $0.26 and $0.118; the cache-heavy agent loop costs $0.36 and $0.16. Costs use the listed standard API rates.
GPT-5.6 Sol has the larger documented context window: 1.05M, compared with 500K.
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Gert Labs
Shared sourceGPT-5.6 Sol leads this result
Terminal-Bench 4.1
Shared sourceGPT-5.6 Sol leads this result
LifeVal
Not directly comparable
Terminal-Bench 3.0
Shared sourceGPT-5.6 Sol leads this result
Terminal-Bench 2.1
GPT-5.6 Sol leads this result
BrowseComp
Not directly comparable
OSWorld 2.0
Not directly comparable
CyberGym
Not directly comparable
ExploitGym
Not directly comparable
Toolathlon
Not directly comparable
Terminal-Bench 2.1 (Vals)
GPT-5.6 Sol leads this result
ApprenticeBench
Not directly comparable
MazeBench
Not directly comparable
deepSwe
Not directly comparable
Bug Hunt Bench
Not directly comparable
SWE-bench Pro
Grok 4.5 leads this result
Terminal-Bench 2.1
GPT-5.6 Sol leads this result
DeepSWE
Not directly comparable
FrontierCode 1.1 Extended
Not directly comparable
FrontierSWE v2
Not directly comparable
CursorBench 3.2
Shared sourceGPT-5.6 Sol leads this result
VulcanBench v3
Shared sourceGrok 4.5 leads this result
VulcanBench CII v1
Not directly comparable
LiveCodeBench (Vals)
Grok 4.5 leads this result
SWE-bench (Vals)
GPT-5.6 Sol leads this result
CursorBench 4.0
Not directly comparable
PostTrainBench v1.1
Shared sourceGPT-5.6 Sol leads this result
FrontierCode 2.0
Not directly comparable
VulcanBench Frontier v4
Not directly comparable
PostTrainBench
Shared sourceGPT-5.6 Sol leads this result
CursorBench 4.1
Not directly comparable
SWE Multilingual
Not directly comparable
BioBasicsBench
Not directly comparable
ARC-AGI-2
GPT-5.6 Sol leads this result
ARC-AGI-3
GPT-5.6 Sol leads this result
GeneBench-Pro
Not directly comparable
ARC-AGI-1
GPT-5.6 Sol leads this result
GPQA
Not directly comparable
GPQA-D
Not directly comparable
HLE-Verified
Not directly comparable
LABBench2
Not directly comparable
HealthBench Professional
Not directly comparable
HealthBench Hard
Not directly comparable
GPQA Diamond (Vals)
GPT-5.6 Sol leads this result
MMLU-Pro (Vals)
Grok 4.5 leads this result
Gray Swan IPI (15 attempts)
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