Model comparison
Gemini 3.1 Pro vs GPT-6 Astra
Google against OpenAI, compared on context, price, and attributed benchmark results.
Recorded profile verification October 1, 2026Individual provider fields may changeEvidence confidence: Medium — see receipts below
Gemini 3.1 Pro
Frontier
OpenAI
GPT-6 Astra
Frontier
| Specification | Gemini 3.1 Pro | GPT-6 Astra |
|---|---|---|
| Provider | ||
| Provider | OpenAI | |
| Tier | ||
| Tier | Frontier | Frontier |
| Context window | ||
| Context window | 1.05M | Winner: 1.05M |
| Max output | ||
| Max output | 66K | Winner: 128K |
| Input / 1M tokens | ||
| Input / 1M tokens | Winner: $2 | $10 |
| Output / 1M tokens | ||
| Output / 1M tokens | Winner: $12 | $50 |
| Weights | ||
| Weights | Closed | Closed |
| Parameters | ||
| Parameters | Not verifiedUnverified | Not verifiedUnverified |
| Reasoning levels | ||
| Reasoning levels | low, medium, high | low, medium, high, xhigh, max |
| Modalities | ||
| Modalities | text, image, video, audio, pdf | text, image |
| API model id | ||
| API model id | gemini-3.1-pro-preview | gpt-6-astra |
| Released | ||
| Released | February 19, 2026 | September 3, 2026 |
| SWE-bench Verified · source date Gemini 3.1 Pro: 2026-02 | ||
| SWE-bench Verified · source date Gemini 3.1 Pro: 2026-02 | 80.6 | Not verifiedUnverified |
| GPQA Diamond · source date Gemini 3.1 Pro: 2026-02, GPT-6 Astra: 2026-09-03 (comparability not verified) | ||
| GPQA Diamond · source date Gemini 3.1 Pro: 2026-02, GPT-6 Astra: 2026-09-03 (comparability not verified) | 94.3 | 96 |
| Humanity's Last Exam · source date Gemini 3.1 Pro: 2026-02, GPT-6 Astra: 2026-09-03 (comparability not verified) | ||
| Humanity's Last Exam · source date Gemini 3.1 Pro: 2026-02, GPT-6 Astra: 2026-09-03 (comparability not verified) | 44.4 | 57.2 |
| Terminal-Bench 2.1 · source date Gemini 3.1 Pro: 2026-07 | ||
| Terminal-Bench 2.1 · source date Gemini 3.1 Pro: 2026-07 | 73.8 | Not verifiedUnverified |
| Artificial Analysis Intelligence Index [max] · source date GPT-6 Astra: 2026-10-01 | ||
| Artificial Analysis Intelligence Index [max] · source date GPT-6 Astra: 2026-10-01 | Not verifiedUnverified | 53 |
| DeepSWE 1.1 · source date GPT-6 Astra: 2026-09-03 | ||
| DeepSWE 1.1 · source date GPT-6 Astra: 2026-09-03 | Not verifiedUnverified | 74.1 |
| OSWorld 2.0 (offline) · source date GPT-6 Astra: 2026-09-03 | ||
| OSWorld 2.0 (offline) · source date GPT-6 Astra: 2026-09-03 | Not verifiedUnverified | 72.6 |
Dates beside benchmark scores refer to the linked source’s publication or capture date unless that source explicitly states when it measured the result. A shared URL alone does not establish comparable runs; unverified setups are marked. Prices are USD per million tokens at standard rates, excluding batch and caching discounts. Values we could not confirm from the provider are shown as “Not verified” rather than estimated.
Benchmark receipts
Where each score comes from, and how far it can be compared across models.
- Source date2026-10-01Artificial Analysis (GPT-6 Astra (max))
Composite index blending reasoning, knowledge, and coding evals into one 0–100 score.
Comparable with caveatOnly same-version scores are comparable. v4.3.2 was rebaselined (the top score fell from 66 on v4.1.1 to ~58), so v4.1.1 figures must not be compared with v4.3.2 figures — check the cited source and its date.
- Source date2026-09-03OpenAI GPT-6 Astra evaluation table (vendor-reported, with tools; maximum across evaluated efforts)
Frontier-knowledge ceiling: extremely hard multi-domain questions written to be near-impossible without deep expertise.
Comparable with caveatSubset/tool configurations (text-only vs with-tools) differ between vendors and materially change scores; must match configuration to compare.
- Source date2026-09-03OpenAI GPT-6 Astra evaluation table (vendor-reported; maximum across evaluated efforts)
Graduate-level science reasoning: multiple-choice questions written by domain PhDs.
Comparable with caveatDo not treat a fixed two-point band as universal measurement uncertainty; it depends on run count and evaluation setup. Chain-of-thought, prompt, and tool policy must match. The small pool limits fine-grained conclusions, and frontier scores can be near ceiling; Artificial Analysis dropped it from its Intelligence Index in v4.3.
- Source date2026-09-03OpenAI (vendor-reported) (v2026.08.08 offline set, partial reward; vendor research/API evaluation, maximum across evaluated efforts)
Computer-use: completing real OS tasks (files, apps, settings) in a sandboxed desktop.
Comparable with caveatOffline vs live interaction modes are NOT comparable; step budgets and screen resolution must match.
- Source date2026-09-03OpenAI (xhigh, mini-swe-agent; matches Datacurve's independent board (74.1% at $4.43/task, rank 1; board updated 2026-09-22))
Agentic software engineering: pass@1 on real repo tasks with reported cost per completed task.
Directly comparable
- Source date2026-07Google DeepMind model evaluation report (vendor, Terminus-2; own Feb report separately reported TB 2.0 = 68.5 — versions preserved)
Agentic terminal work: multi-step tasks executed in a sandboxed shell environment.
Comparable with caveatNot comparable with Terminal-Bench 3.0 or 4.0 (different task sets) or v1; harness configuration (container, time limits) also shifts results.
- Source date2026-02Google DeepMind model evaluation report (vendor, no tools; 51.4 with search+code)
Frontier-knowledge ceiling: extremely hard multi-domain questions written to be near-impossible without deep expertise.
Comparable with caveatSubset/tool configurations (text-only vs with-tools) differ between vendors and materially change scores; must match configuration to compare.
- Source date2026-02Google DeepMind model evaluation report (vendor, no tools, pass@1)
Graduate-level science reasoning: multiple-choice questions written by domain PhDs.
Comparable with caveatDo not treat a fixed two-point band as universal measurement uncertainty; it depends on run count and evaluation setup. Chain-of-thought, prompt, and tool policy must match. The small pool limits fine-grained conclusions, and frontier scores can be near ceiling; Artificial Analysis dropped it from its Intelligence Index in v4.3.
- Source date2026-02Google DeepMind model evaluation report (vendor, Thinking High, avg of 10 runs, +0.6 disclosed adjustment)
Real GitHub issue resolution: does the model's patch pass the hidden tests.
Comparable with caveatPost-audit vendor claims and pre-audit scores sit on different task trust levels; scaffolding (agent harness, compute budget) also dominates results. Never aggregate across scaffolds.
Pricing tiers
Gemini 3.1 Pro: The current Gemini developer guide lists $2/$12 per MTok below 200K input and $4/$18 above 200K, including thinking output. It leaves the exact 200K boundary unspecified; confirm that boundary and other processing/cache tiers before budgeting. The exact API ID remains gemini-3.1-pro-preview. Restricted Gemini 4 Argon is a separate preview and does not make this endpoint stable.
GPT-6 Astra: Standard $10/$50 per MTok (≤272K input); above 272K the full request bills $20/$75. Cached input $1/$2 and cache writes $12.50/$25 for short/long context. Batch/Flex are half Standard; Fast is 2x. Ultrafast is 6x: $60/$300 short, $120/$450 long, through Responses with global/US processing; no EU or other regional inference residency. Regional/FedRAMP processing adds 10% where eligible. Knowledge cutoff Apr 30 2026. Enterprise model access is disabled by default.
Gemini 3.1 Pro
Gemini 3.1 Pro Preview is Google's multimodal Pro endpoint with a 1,048,576-token input limit and 65,536-token output limit.
Best for
- Very long documents
- Multimodal reasoning
- Frontier knowledge work
Watch out
This API endpoint remains Preview. A separate customtools endpoint is optimized for bash/custom-tool workflows and can behave differently on other tasks. Keep endpoint, thinking level and benchmark version matched; restricted Gemini 4 Argon access is a separate lifecycle.
GPT-6 Astra
OpenAI describes GPT-6 Astra as its most capable model for complex reasoning, coding and computer use, and the first it gates at the Preparedness Framework's 'Critical' cybersecurity threshold.
Best for
- Computer-use agents
- Agentic coding
- Hard reasoning
Watch out
OpenAI places Astra at its Critical cybersecurity threshold and disables it by default for Enterprise. Tool calling requires Responses; none reasoning and custom temperature/top_p/logprobs are unsupported. Long prompts above 272K increase the full-request rate. GPT-6.1 Sol has lower base token prices; compare results on your own workload.
Benchmark
DeepSWE 1.1 in context
Only GPT-6 Astra has a published DeepSWE 1.1 result. It is shown against the wider field, with cost per completed task alongside the score.
Local leader
GPT-6 Astra [xhigh]
74.1%
Rows shown
28
Best source-matched Pass@1 per model
Snapshot date
2026-10-01
Mirrored from deepswe.datacurve.ai
Better is toward the top-right (higher pass rate, lower cost). X-axis is reversed to match DeepSWE’s public chart. v1.1 uses average cost, output tokens and steps. Legacy v1 transcriptions are excluded here until an exact primary receipt is retained.
| # | Model | Pass@1 | Cost / task | Tokens / task | Steps / task |
|---|---|---|---|---|---|
| 1 | GPT-6 Astra [xhigh] | 74.1% | $4.43 | 30k | 29 |
| 2 | Gemini 3.8 Flash [high] | 73.8% | $2.36 | 143k | 166 |
| 3 | Claude Opus 5 [max] | 73.6% | $11.84 | 118k | 99 |
| 4 | GPT-5.6 Sol [max] | 72.7% | $8.39 | 60k | 61 |
| 5 | Claude Fable 5 [xhigh] | 69.9% | $13.41 | 80k | 68 |
| 6 | GPT-5.6 Terra [max] | 69.6% | $4.95 | 72k | 76 |
| 7 | GLM 5.3 [max] | 69.0% | $3.99 | 80k | 124 |
| 8 | Kimi K3 [max] | 68.5% | $4.65 | 82k | 98 |
| 9 | Grok 4.6 [medium] | 67.5% | $3.45 | 50k | 70 |
| 10 | GPT-5.6 Luna [max] | 67.2% | $3.03 | 73k | 102 |
| 11 | GPT-5.5 [xhigh] | 67.0% | $7.23 | 46k | 82 |
| 12 | Gemini 3.7 Flash [medium] | 65.5% | $2.03 | 94k | 117 |
| 13 | GLM 5.3 Flash [max] | 63.4% | $0.48 | 73k | 123 |
| 14 | DeepSeek V4-Pro [max] | 62.8% | $0.24 | 106k | 155 |
| 15 | Claude Opus 4.8 [max] | 59.0% | $13.22 | 135k | 120 |
| 16 | Qwen3.8-Max [xhigh] | 57.5% | $3.73 | 95k | 111 |
| 17 | Muse Spark 1.2 [xhigh] | 54.9% | $3.70 | 99k | 101 |
| 18 | Claude Sonnet 5 [max] | 53.8% | $26.40 | 214k | 268 |
| 19 | Grok 4.5 [high] | 53.8% | $2.42 | 36k | 61 |
| 20 | DeepSeek V4-Flash [max] | 53.3% | $0.10 | 108k | 153 |
| 21 | Muse Spark 1.1 [xhigh] | 53.3% | $2.36 | 74k | 96 |
| 22 | GPT-5.4 [xhigh] | 51.8% | $5.65 | 71k | 70 |
| 23 | Gemini 3.6 Flash [high] | 46.7% | $4.42 | 96k | 117 |
| 24 | GLM 5.2 [max] | 43.8% | $3.92 | 78k | 129 |
| 25 | Gemini 3.5 Flash [high] | 36.1% | $3.45 | 76k | 105 |
| 26 | Kimi K2.7 Code | 30.5% | $2.82 | 59k | 149 |
| 27 | Claude Sonnet 4.6 [high] | 29.9% | $5.52 | 76k | 134 |
| 28 | Gemini 3.1 Pro [high] | 11.7% | $2.14 | 28k | 76 |
“Best per model” shows each model’s highest source-matched Pass@1 in this capture; switch to all effort levels to see every retained configuration. Efforts differ across models, so this view is not a comparison at matched effort. The source was generated September 22 and captured October 1. Small gaps may not be statistically meaningful — confirm on deepswe.datacurve.ai.
When the cheaper one wins
Gemini 3.1 Pro is cheaper on output at $12 per million tokens against $50 for GPT-6 Astra — about 4.2×. Use the cheaper tier for classification, extraction, summarisation, and any task where the expensive model’s extra score does not change the accepted output. The expensive one only pays if your hardest task actually fails on the cheap tier. On DeepSWE 1.1, Gemini 3.1 Pro is 11.7% Pass@1 at $2.14/task versus GPT-6 Astra at 74.1% / $4.43/task. This compares standard short-context token rates, not total cost per accepted task. Include input, cache, context tiers, schedules, retries and review in your pilot.
Run the model pickerEvidence confidence: Medium
How strong and complete the evidence behind this comparison is — not a prediction of which model is better.
- Pricing verified on both sides — Input and output rates are verified for both models.
- 4/5 core specs verified on both sides — Not published for at least one side: parameter count.
- No directly aligned benchmark setup — No benchmark has matching cited sources, source dates, units, effort and recorded run details on both models.
- Verified within the last 90 days — Older of the two catalog checks was 25 days ago.
- Both models carry source citations — Each side has at least two catalog sources on record.
Source receipts
Each catalog figure was checked against the provider or an independent second source on the date shown.
- Gemini 3.1 Pro: Google primary profile — whole-record source check October 1 (accessed 2026-10-01)
- Gemini 3.1 Pro: Gemini current API pricing and cache-storage tiers (accessed 2026-10-01)
- Gemini 3.1 Pro: Gemini developer guide — exact Preview rates and boundary limitation (accessed 2026-10-01)
- Gemini 3.1 Pro: Gemini API 3.1 Pro Preview — exact endpoint and customtools scope (accessed 2026-10-01)
- Gemini 3.1 Pro: Google Cloud — Gemini 3.1 Pro (accessed 2026-08-29)
- Gemini 3.1 Pro: TechCrunch — Gemini 3.1 Pro (accessed 2026-08-29)
- GPT-6 Astra: OpenAI model card — whole-profile source check October 1 (accessed 2026-10-01)
- GPT-6 Astra: OpenAI current API pricing and processing tiers (accessed 2026-10-01)
- GPT-6 Astra: OpenAI API changelog — September 3 release; checked October 1 (accessed 2026-10-01)
- GPT-6 Astra: OpenAI — Introducing GPT-6 Astra (accessed 2026-09-03)
- GPT-6 Astra: OpenAI API pricing (gpt-6-astra $10/$50) (accessed 2026-09-03)
- GPT-6 Astra: CNBC — OpenAI launches GPT-6 Astra (accessed 2026-09-03)
- GPT-6 Astra: OpenAI model docs — gpt-6-astra (128K max output, effort levels) (accessed 2026-09-05)
- GPT-6 Astra: OpenAI API pricing (gpt-6-astra ≤272K $10/$50, >272K $20/$75) (accessed 2026-09-26)
Related comparisons
- Claude Fable 5.1 vs Gemini 3.1 Pro
- Claude Fable 5.1 vs GPT-6 Astra
- Claude Fable 5 vs Gemini 3.1 Pro
- Claude Fable 5 vs GPT-6 Astra
- Claude Mythos 5.1 vs Gemini 3.1 Pro
- Claude Mythos 5.1 vs GPT-6 Astra
Diving deeper on one model? Gemini 3.1 Pro · GPT-6 Astra
Common questions
Gemini 3.1 Pro vs GPT-6 Astra
Answered from the verified figures on this page rather than general guidance.
Is Gemini 3.1 Pro or GPT-6 Astra cheaper for input?
Is Gemini 3.1 Pro or GPT-6 Astra cheaper for output?
Which has the larger context window, Gemini 3.1 Pro or GPT-6 Astra?
Do Gemini 3.1 Pro and GPT-6 Astra support the same reasoning levels?
Should I use Gemini 3.1 Pro or GPT-6 Astra?
Next step
Choosing between them
The verified figures that separate this pair, computed from the catalog rather than restated boilerplate.
- Input price: Gemini 3.1 Pro costs $2 per 1M tokens versus $10 for GPT-6 Astra — a 5x difference at the headline tier.
- Context: GPT-6 Astra takes 1.05M against 1.05M for Gemini 3.1 Pro — only decisive if your prompts approach the smaller window.
Choosing a harness rather than a model — Cursor, Copilot, Claude Code, Windsurf, or Lovable? Compare agentic harnesses · Latest releases.