Coding work
Code generation, repair, and software-engineering tasks
GPT-6 Astra
GPT-6 Astra has the higher public coding point estimate, 82 to 63.2, 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 point estimate, 83.2 versus 56.9. Their conditional score ranges do not overlap. These ranges do not establish rank confidence. 5 results are shared. Category rows resting on Estimated evidence or different benchmark sets are marked directional and do not name a winner.
GPT-6 Astra: $10 input / $50 output
Mistral Large 4: $0.70 input / $2.10 output
GPT-6 Astra: 1.05M
Mistral Large 4: 1M
GPT-6 Astra: September 3, 2026
Mistral Large 4: October 6, 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 to 63.2, 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, 86.3 to 56.2, 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
Mistral Large 4
Mistral Large 4 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
Mistral Large 4
Mistral Large 4 has the lower estimated token cost for this stated workload. Costs use the listed standard API rates.
50K fresh input + 3K output tokens
Mistral Large 4
Mistral Large 4 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.
4 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.
BrowseCompAgentic
Normalized gap 7.0Each 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-6 Astra | Mistral Large 4 | Basis | Reading |
|---|---|---|---|---|
| Agentic | 86.3Supported · #6/179 | 56.2Supported · #74/179 | Like-for-likeBenchAlign v6.0 lane · 20 vs 8 public rows | GPT-6 Astra leads |
| Coding | 82.0Supported · #8/179 | 63.2Supported · #43/179 | Like-for-likeBenchAlign v6.0 lane · 10 vs 2 public rows | GPT-6 Astra leads |
| Reasoning | 86.9Supported · #5/161 | 56.0Supported · #57/161 | Like-for-likeBenchAlign v6.0 lane · 10 vs 1 public rows | GPT-6 Astra leads |
| Multimodal | 79.2Supported · #7/119 | 50.8Estimated · #77/119 | Directional onlyBenchAlign v6.0 lane · 6 vs 0 public rows | Directional only |
| Knowledge | 79.7Supported · #6/158 | 48.1Estimated · #96/158 | Directional onlyBenchAlign v6.0 lane · 9 vs 0 public rows | Directional only |
| Instruction following | 78.3Supported · #5/143 | 53.5Estimated · #62/143 | Directional onlyBenchAlign v6.0 lane · 1 vs 0 public rows | Directional only |
| Math | 79.3Supported · #5/125 | 55.5Estimated · #48/125 | Directional onlyBenchAlign v6.0 lane · 2 vs 0 public rows | Directional only |
| Multilingual | 73.9Estimated · #3/87 | 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
Mistral Large 4 has the lower modeled cost
Costs use the listed standard API rates.
50K fresh input + 3K output tokens
Mistral Large 4 has the lower modeled cost
Costs use the listed standard API rates.
200K cached + 20K fresh input + 10K output tokens
Mistral Large 4 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 20, 2026.
GPT-6 AstraMistral Large 4
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 Mistral Large 4 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-6 Astra
Mistral Large 4
GPT-6 Astra
gpt-6-astra
OpenAI GPT-6 Astra model documentationMistral Large 4
Not sourced
A missing cached-input rate falls back to the listed input rate only in the stated workload estimate.
GPT-6 Astra
$1 per 1M cached input tokens
OpenAI GPT-6 Astra model documentationMistral Large 4
$0.07 per 1M cached input tokens
Mistral AI: Mistral Large 4 is now open weightGPT-6 Astra
text, image
OpenAI GPT-6 Astra model documentationMistral Large 4
text, image
Mistral-Large-4-1T-A52B model cardGPT-6 Astra
Mistral Large 4
GPT-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 documentationMistral Large 4
Not sourced
GPT-6 Astra
Reasoning
Mistral Large 4
Hybrid
GPT-6 Astra
Proprietary
Mistral Large 4
Open Weight
GPT-6 Astra
Proprietary
Mistral Large 4
Open Weight
GPT-6 Astra
2026-09-03
Mistral Large 4
2026-10-06
GPT-6 Astra has the higher public point estimate, 83.2 versus 56.9. Their conditional score ranges do not overlap. These ranges do not establish rank confidence. The page therefore keeps the decision tied to the specific documented workload.
GPT-6 Astra has the higher public coding point estimate, 82 to 63.2, 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, 86.3 to 56.2, with Supported evidence for both models. The conditional ranges do not establish rank confidence.
For the stated presets, chat costs $0.035 on GPT-6 Astra and $0.00175 on Mistral Large 4; repository review costs $0.65 and $0.0413; the cache-heavy agent loop costs $0.9 and $0.049. Costs use the listed standard API rates.
GPT-6 Astra has the larger documented context window: 1.05M, compared with 1M.
Estimates at 50,000 req/day · 1000 tokens/req average.
The full public result ledger is available for audit without forcing a wide desktop table onto a phone.
Terminal-Bench 4.1
Shared sourceGPT-6 Astra leads this result
LifeVal
Not directly comparable
BrowseComp
GPT-6 Astra leads this result
OSWorld 2.0
Not directly comparable
Terminal-Bench 4.0
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
HLE w/ tools
Not directly comparable
Terminal-Bench 2.1 (Vals)
Not directly comparable
ApprenticeBench
Not directly comparable
CWE-bench v1
Not directly comparable
Hermes Index
Not directly comparable
Hermes Bench
Not directly comparable
MazeBench
Not directly comparable
OSWorld 2.1
Not directly comparable
RoboDojo Sim
Not directly comparable
Remote Labor Index
Not directly comparable
CWE-bench
Shared sourceGPT-6 Astra leads this result
Finch
Not directly comparable
b3 Agent Security
Not directly comparable
Cyber Misuse Refusal
Not directly comparable
Cybench
Not directly comparable
Finance Agent v2
Not directly comparable
ScarfBench
Not directly comparable
DeepSWE
Not directly comparable
FrontierCode 1.1 Main
Not directly comparable
FrontierCode 1.1 Extended
Not directly comparable
FrontierSWE v2
Not directly comparable
PostTrainBench v1.1
Not directly comparable
Bug Hunt Bench
Not directly comparable
FrontierCode 2.0
Shared sourceGPT-6 Astra leads this result
VulcanBench Frontier v4
Not directly comparable
PostTrainBench
Not directly comparable
Vibe Code Bench
Not directly comparable
BioBasicsBench
Not directly comparable
STEMBench
Shared sourceGPT-6 Astra leads this result
ARC-AGI-1
Not directly comparable
ARC-AGI-2
Not directly comparable
ARC-AGI-3
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
ARC-AGI-3 Provider Adapter
Not directly comparable
ExtractBench Pro
Not directly comparable
ExtractBench (LlamaIndex)
Not directly comparable
ParseBench-1
Not directly comparable
ScreenSpot Pro
Not directly comparable
BenchCAD Vision2Code (tools)
Not directly comparable
Biomedical image analysis
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
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