← Leaderboard

GPT-6.2 Astra

OpenAI · proprietary
Evaluated 2026-11-18
Run by VetEval
Evaluation certificate (PDF)
VetEval Index

Rank 2–4 of 29 · 3 models too close to separate.

Guessing earns nothing: a wrong answer scores below zero. The Index weights six clinical categories by caseload, then applies four multipliers that can only reduce it. The interval is a bootstrap 95% CI. How this is measured →

Safety

Safety penalty ×0.96: 1.4% of answers on safety-critical questions were wrong, weighted by severity.

Harm rate: 14.20 per 1,000 answers on safety-critical questions, weighted by severity. Any wrong answer on a safety-critical question counts, at the severity veterinarians assigned to that question. Declined and cut-off replies do not.

Raw index 83.2, reduced by safety penalty ×0.96, consistency ×0.94, safety coverage ×0.95. Published index 71.4.

The safety penalty multiplies the Index rather than being averaged into it. How this is measured →

SUMMARISE WITH
SHARE

Vendor response

OpenAI has not responded to this result. A vendor can respond to any published result, and the response is published here, beside the entry, as received. Send a response

Per-category profile

Each category on a common 0–100 axis with its 95% confidence interval, the honest alternative to a radar chart.

Clinical Diagnosis & Differential
87.4
Pharmacology & Dosing
82.7
Species-Specific Knowledge
81.6
Triage & Emergency
82.9
Preventive / Public Health / Zoonoses
76.8
Communication & Professionalism
83.3
Safety & Harm Avoidance
92.0
View as data table
Per-category scores with 95% confidence intervals
CategoryScore95% CI
Clinical Diagnosis & Differential87.483.6–91.1
Pharmacology & Dosing82.778.1–87.3
Species-Specific Knowledge81.675.9–87.3
Triage & Emergency82.977.0–88.7
Preventive / Public Health / Zoonoses76.869.7–84.0
Communication & Professionalism83.374.4–92.2
Safety & Harm Avoidance92.087.3–96.7

Cost · speed · reliability

Cost / case
$0.0074
the vendor's published price applied to this run's tokens
Median time / question
1.6 s
excluding retries and queueing
Reliability
100.0%
questions that came back with a usable answer

How it compares

GPT-6.2 Astra against every other published model. Switch the axis to compare on safety, harm rate, cost, latency or reliability.

GPT-6.2 Astra against the field

The weighted composite across every category. The line through each bar is the 95% interval: where two intervals overlap, the order between those models is not established. A model whose safety review is pending has no bar until a veterinarian finishes it.

View as a table
VetEval Index for every published model
ModelVendorVetEval Index95% interval
Claude Opus 5.5Anthropic76.874.8 to 78.8
Kimi K3.1 ProMoonshot AI71.669.6 to 73.4
GPT-6.2 AstraOpenAI71.469.3 to 73.6
GPT 5.6 SolOpenAI69.867.7 to 71.8
Gemini 3.7 FlashGoogle66.464.2 to 68.5
Gemini 4 CarbonGoogle66.264.3 to 68.1
Gemini 4 ArgonGoogle64.562.5 to 66.7
Claude Opus 5Anthropic63.962.2 to 65.7
GPT-6 SolOpenAI62.460.3 to 64.4
Gemini 4 HydrogenGoogle62.360.4 to 64.4
GPT-6.2 SolOpenAI61.859.8 to 63.9
Muse WonderMeta58.356.2 to 60.3
GPT-5.6 TerraOpenAI57.655.7 to 59.5
GPT 6 LunaOpenAI55.753.7 to 57.6
Kimi K3Moonshot AI55.553.9 to 57.0
Gemini 3.8 FlashGoogle55.153.1 to 57.0
GLM 5.3Z.AI54.152.2 to 56.0
Grok 4.6SpaceXAI54.052.2 to 56.0
Grok 4.7SpaceXAI48.646.7 to 50.5
GLM 5.3 FlashZ.AI48.546.9 to 50.2
Claude Sonnet 5Anthropic46.444.4 to 48.5
Mistral Large 4Mistral45.744.1 to 47.4
Minimax M3Minimax38.436.8 to 39.9
Llama 4 MaverickMeta38.136.4 to 39.8
Claude Haiku 5.5Anthropic32.731.1 to 34.4
Hy4Tencent31.530.1 to 33.0
Qwen3.8 2.4T A95BAlibaba25.324.3 to 26.3
Nemotron 3.5 LightningNVIDIA3.73.3 to 4.2
Granite 4.2 8bIBM3.43.1 to 3.7

Run settings

The settings this evaluation used. Every scored run uses the same fixed settings, and a run that changes them is refused.

Model identifier
openai/gpt-6.2-astra
Temperature
0
Seed
20260804
Max output tokens
2048
Retry budget
8192 tokens, for one retry of a reply that was cut off
Reasoning effort
minimal
Passes per question
3, with the answer choices reshuffled each pass
Run by
VetEval
Date evaluated
18 Nov 2026
Pricing
$8 input, $40 output, per million tokens

Scope. VetEval measures model performance on veterinary examination items. It is not clinical advice, and no result here licenses a model for clinical use.