Coding work
Code generation, repair, and software-engineering tasks
GPT-6 Astra
GPT-6 Astra has the higher public coding point estimate, 82.2 to 67.9, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Updated November 21, 2026. Rank says GPT-6 Astra is ahead. Price, access, and your workload can each overturn that. Public scores include evidence status and uncertainty.
GPT-6 Astra has the higher public score, 83.6 versus 63.5, and the 90% score intervals do not overlap. 19 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
Claude Haiku 5.5: $0.10 input / $0.50 output
GPT-6 Astra: $10 input / $50 output
Claude Haiku 5.5: 1M
GPT-6 Astra: 1.05M
Claude Haiku 5.5: October 7, 2026
GPT-6 Astra: September 3, 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-6 Astra
GPT-6 Astra has the higher public coding point estimate, 82.2 to 67.9, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Tool use, computer use, and multi-step task completion
GPT-6 Astra
GPT-6 Astra has the higher public agentic point estimate, 87.3 to 68.3, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
Prompts that approach the documented context limit
GPT-6 Astra
GPT-6 Astra has the larger documented context window.
1K fresh input + 500 output tokens
Claude Haiku 5.5
Claude Haiku 5.5 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
Claude Haiku 5.5
Claude Haiku 5.5 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
50K fresh input + 3K output tokens
Claude Haiku 5.5
Claude Haiku 5.5 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-6 Astra 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.
ARC-AGI-3Reasoning
Normalized gap 62.3FrontierMath v2 (Tier 4)Math
Normalized gap 51.3ARC-AGI-2Reasoning
Normalized gap 33.7FrontierMath v2 (Tiers 1-3)Math
Normalized gap 18.6Each 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 | Claude Haiku 5.5 | GPT-6 Astra | Basis | Reading |
|---|---|---|---|---|
| Agentic | 68.3Supported · #25/182 | 87.3Supported · #5/182 | Like-for-likeBenchAlign v6.0 lane · 9 vs 21 public rows | GPT-6 Astra leads |
| Coding | 67.9Supported · #28/180 | 82.2Supported · #8/180 | Like-for-likeBenchAlign v6.0 lane · 7 vs 10 public rows | GPT-6 Astra leads |
| Reasoning | 62.6Supported · #38/161 | 87.0Supported · #5/161 | Like-for-likeBenchAlign v6.0 lane · 4 vs 10 public rows | GPT-6 Astra leads |
| Multimodal | 63.9Supported · #39/119 | 79.2Supported · #7/119 | Like-for-likeBenchAlign v6.0 lane · 4 vs 6 public rows | GPT-6 Astra leads · intervals overlap |
| Knowledge | 50.2Supported · #84/158 | 80.0Supported · #6/158 | Like-for-likeBenchAlign v6.0 lane · 1 vs 9 public rows | GPT-6 Astra leads |
| Instruction following | 58.3Supported · #37/143 | 78.6Supported · #5/143 | Like-for-likeBenchAlign v6.0 lane · 0 vs 1 public rows | GPT-6 Astra leads · intervals overlap |
| Math | 62.1Supported · #29/125 | 79.6Supported · #5/125 | Like-for-likeBenchAlign v6.0 lane · 2 vs 2 public rows | GPT-6 Astra leads · intervals overlap |
| Multilingual | 56.1Estimated · #36/88 | 74.1Estimated · #3/88 | 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
Claude Haiku 5.5 has the lower modeled cost
Costs use the listed standard API rates.
50K fresh input + 3K output tokens
Claude Haiku 5.5 has the lower modeled cost
Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
Claude Haiku 5.5 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.
Claude Haiku 5.5GPT-6 Astra
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-6 Astra 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.
Claude Haiku 5.5
GPT-6 Astra
Claude Haiku 5.5
claude-haiku-5-5
Anthropic Claude Haiku 5.5 model documentationGPT-6 Astra
gpt-6-astra
OpenAI GPT-6 Astra model documentationA missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
Claude Haiku 5.5
$0.01 per 1M cached input tokens
Claude API pricingGPT-6 Astra
$1 per 1M cached input tokens
OpenAI GPT-6 Astra model documentationClaude Haiku 5.5
GPT-6 Astra
text, image
OpenAI GPT-6 Astra model documentationClaude Haiku 5.5
GPT-6 Astra
Claude Haiku 5.5
Generally Available · Claude API, Amazon Bedrock, Google Cloud, Microsoft Foundry, Claude Platform on AWS
Anthropic Claude Haiku 5.5 model documentationGPT-6 Astra
Limited Availability · OpenAI Responses API, OpenAI Chat Completions API, ChatGPT Plus, Pro, Business, and Enterprise, Microsoft Azure, AWS Bedrock
OpenAI GPT-6 Astra model documentationClaude Haiku 5.5
Reasoning
GPT-6 Astra
Reasoning
Claude Haiku 5.5
Proprietary
GPT-6 Astra
Proprietary
Claude Haiku 5.5
Proprietary
GPT-6 Astra
Proprietary
Claude Haiku 5.5
2026-10-07
GPT-6 Astra
2026-09-03
GPT-6 Astra has the higher public score, 83.6 versus 63.5, and the 90% score intervals do not overlap. That is the clearest overall quality signal in the current public data.
GPT-6 Astra has the higher public coding point estimate, 82.2 to 67.9, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
GPT-6 Astra has the higher public agentic tasks point estimate, 87.3 to 68.3, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
For the stated presets, chat costs $0.00035 on Claude Haiku 5.5 and $0.035 on GPT-6 Astra; repository review costs $0.0065 and $0.65; the cache-heavy agent loop costs $0.009 and $0.9. Costs use the listed standard API rates.
GPT-6 Astra has the larger documented context window: 1.05M, compared with 1M.
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Gert Labs
Shared sourceGPT-6 Astra leads this result
Terminal-Bench 4.1
Shared sourceGPT-6 Astra leads this result
Agents' Last Exam (Linux)
Not directly comparable
Terminal-Bench 4.0
GPT-6 Astra leads this result
HLE w/ tools
Claude Haiku 5.5 leads this result
MazeBench
GPT-6 Astra leads this result
Hermes Index
Shared sourceGPT-6 Astra leads this result
Hermes Bench
Shared sourceGPT-6 Astra leads this result
OSWorld 2.1 Offline
Not directly comparable
LifeVal
Not directly comparable
BrowseComp
Not directly comparable
OSWorld 2.0
Not directly comparable
Terminal-Bench-Science 0.1
Not directly comparable
ExploitGym
Not directly comparable
Agents' Last Exam
Not directly comparable
AutomationBench
Not directly comparable
Terminal-Bench 2.1 (Vals)
Not directly comparable
ApprenticeBench
Not directly comparable
CWE-bench v1
Not directly comparable
OSWorld 2.1
Not directly comparable
RoboDojo Sim
Not directly comparable
Remote Labor Index
Not directly comparable
CWE-bench
Not directly comparable
FrontierCode 1.1 Main
GPT-6 Astra leads this result
Bug Hunt Bench
Shared sourceGPT-6 Astra leads this result
FrontierSWE v2
Shared sourceGPT-6 Astra leads this result
FrontierCode 2.0
Shared sourceGPT-6 Astra leads this result
CursorBench 4.0
Not directly comparable
VulcanBench Frontier v4
Shared sourceClaude Haiku 5.5 leads this result
CursorBench 4.1
Not directly comparable
ScarfBench
Not directly comparable
DeepSWE
Not directly comparable
FrontierCode 1.1 Extended
Not directly comparable
PostTrainBench v1.1
Not directly comparable
PostTrainBench
Not directly comparable
ARC-AGI-1
GPT-6 Astra leads this result
ARC-AGI-2
GPT-6 Astra leads this result
ARC-AGI-3
GPT-6 Astra leads this result
ARC-AGI-3 Provider Adapter
GPT-6 Astra leads this result
BioBasicsBench
Not directly comparable
STEMBench
Not directly comparable
GeneBench-Pro
Not directly comparable
MRCR v2 256K-512K
Not directly comparable
MRCR v2 512K-1M
Not directly comparable
GraphWalks BFS 256K–1M
Not directly comparable
ParseBench-2
Not directly comparable
PerceptionBench (tools)
Not directly comparable
ParseBench-1
Shared sourceGPT-6 Astra leads this result
Chartography (no tools)
Not directly comparable
ExtractBench Pro
Not directly comparable
ExtractBench (LlamaIndex)
Not directly comparable
ScreenSpot Pro
Not directly comparable
BenchCAD Vision2Code (tools)
Not directly comparable
Biomedical image analysis
Not directly comparable
HLE w/o tools
Not directly comparable
GPQA
Not directly comparable
GPQA-D
Not directly comparable
HealthBench (raw)
Not directly comparable
HealthBench (length-adjusted)
Not directly comparable
HealthBench Professional
Not directly comparable
HealthBench Professional (raw)
Not directly comparable
HealthBench Hard
Not directly comparable
PhysicianBench
Not directly comparable
Morphology-to-molecule matching
Not directly comparable
Gray Swan IPI (15 attempts)
Not directly comparable
FrontierMath v2 (Tiers 1-3)
Shared sourceGPT-6 Astra leads this result
FrontierMath v2 (Tier 4)
GPT-6 Astra leads this result
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