GPT-5.4 vs GPT-6 Astra vs Gemini 3.1 Pro Preview
Too close to call on our weighted score (Gemini 3.1 Pro Preview 68, GPT-6 Astra 66, GPT-5.4 65). The right pick depends on what you value most.GPT-6 Astra comes out ahead, 89 to 84 and 82 on our weighted score, though Gemini 3.1 Pro Preview is 4.4× cheaper per token.
OpenAI
GPT-5.4
65/100- ECI157.9
- Price$2.50 / $15.00
- Context1.05M
OpenAI
GPT-6 Astra
66/100- ECI169.2
- Price$10.00 / $50.00
- Context1.05M
Google
Gemini 3.1 Pro Preview
68/100- ECI156.3
- Price$2.00 / $12.00
- Context1.05M
OpenAI
GPT-5.4
82/100- ECI157.9
- Price$2.50 / $15.00
- Context1.05M
- Our pick
OpenAI
GPT-6 Astra
89/100- ECI169.2
- Price$10.00 / $50.00
- Context1.05M
Google
Gemini 3.1 Pro Preview
84/100- ECI156.3
- Price$2.00 / $12.00
- Context1.05M
Too close to callGPT-6 Astra is our pick
It is close. Our weighted score puts them within 1 points (Gemini 3.1 Pro Preview 68/100, GPT-6 Astra 66/100, GPT-5.4 65/100), so choose by what matters most for your work: GPT-6 Astra for raw capability and Gemini 3.1 Pro Preview on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.GPT-6 Astra is the better all-round choice, scoring 89/100 against Gemini 3.1 Pro Preview (84) and GPT-5.4 (82). It leads on capability. Gemini 3.1 Pro Preview wins on inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.
- CapabilityGPT-6 AstraCapabilities Index (ECI): GPT-6 Astra 169.2 · GPT-5.4 157.9 · Gemini 3.1 Pro Preview 156.3
- Lowest priceGemini 3.1 Pro PreviewGemini 3.1 Pro Preview $4.50 · GPT-5.4 $5.63 · GPT-6 Astra $20.00 per 1M tokens (3:1 blend)
- Longest contextAbout the sameGPT-5.4 1,050,000 · GPT-6 Astra 1,050,000 · Gemini 3.1 Pro Preview 1,048,576 tokens
- Widest inputsGemini 3.1 Pro PreviewGPT-5.4: Text, Images, PDFs · GPT-6 Astra: Text, Images, PDFs · Gemini 3.1 Pro Preview: Text, Images, PDFs, Audio, Video
- Self-hostingNo confirmed open weightsAll three are available only through APIs
| Measure | Weight | GPT-5.4 | GPT-6 Astra | Gemini 3.1 Pro Preview |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 85 | 96 | 84 |
| Price | 25% | 14 | 0 | 18 |
| Inputs & features | 15% | 80 | 80 | 100 |
| Context window | 10% | 65 | 65 | 65 |
| Overall | 100% | 65/100 | 66/100 | 68/100 |
| Measure | Weight | GPT-5.4 | GPT-6 Astra | Gemini 3.1 Pro Preview |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 67% | 85 | 96 | 84 |
| Inputs & features | 20% | 80 | 80 | 100 |
| Context window | 13% | 65 | 65 | 65 |
| Overall | 100% | 82/100 | 89/100 | 84/100 |
Every spec in one table
Highlighted cells lead their row. Unavailable specifications are marked “Not published”. Publisher results include their evaluation settings and source.
| Specification | |||
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 157.9 | 169.2 (best) | 156.3 |
| ECI rank | #29 of 159 | #4 of 159 (best) | #41 of 159 |
| ECI confidence interval | 156.0–160.0 | 166.4–172.5 | 154.5–158.2 |
| ECI evaluation date | Mar 5, 2026 | Sep 3, 2026 | Feb 19, 2026 |
| Documented capabilities | Agent-ready GPT for coding and computer-use workflows at a lower cost | GPT-6 Astra is OpenAI's most capable model for complex reasoning, coding, computer use, research, and document creation. | Reasoning-first Gemini preview for agentic coding and complex problem solving |
| Model parameters | Not published | Not published | Not published |
| Output modalities | Text | Text | Text |
| GPQA DiamondGraduate-level science questions | 93.3%xhigh | 95.8%max (best) | 94.4%high |
| FrontierMath Tiers 1–3Research-level mathematics | 78.6%xhigh | 93.7%max (best) | 59.7% |
| OTIS Mock AIME 2024–2025Competition mathematics | 97.8%high | 100%max (best) | 95.6% |
| SWE-bench VerifiedFixing real GitHub issues | 76.9%high (best) | Not published | 75.6% |
| SimpleQA VerifiedShort factual questions | 45.1%xhigh | 75.6%max (best) | 73.5%high |
| Publisher-reported benchmarks | |||
| SWE-Bench Pro · publicPublisher-reported result | 59.1resolve rateReported result | Not published | 46.1resolve rateReported result |
| SWE-Atlas Codebase QnAPublisher-reported result | 40.8scoreReported result | Not published | 13.5scoreReported result |
| SWE-Atlas RefactoringPublisher-reported result | 44.29scoreReported result | Not published | 33.81scoreReported result |
| SWE-Atlas Test WritingPublisher-reported result | 44.36scoreReported result | Not published | 29.84scoreReported result |
| Artificial Analysis Coding Agent Indexmedium | 53.6average pass@1Reported result | Not published | Not published |
| SWE-Atlas Codebase QnAmedium | 72.4pass@1Reported result | Not published | Not published |
| SWE-Bench Pro · hard-aamedium | 18.4pass@1Reported result | Not published | Not published |
| Terminal-Bench 2.1medium | 69.8pass@1Reported result | Not published | Not published |
| Terminal-Bench 2.0Publisher-reported result | 75.1success rateReported resultApr 23, 2026 | Not published | Not published |
| GPQA DiamondPublisher-reported result | 92.8accuracyReported resultApr 23, 2026 | 96accuracyReported resultSep 3, 2026 | 94.3accuracyReported resultApr 23, 2026 |
| Humanity's Last Examno tools | 39.8accuracyReported resultApr 23, 2026 | Not published | Not published |
| Humanity's Last Examwith tools | 52.1accuracyReported resultApr 23, 2026 | 57.2accuracyReported resultSep 3, 2026 | Not published |
| OSWorld-VerifiedPublisher-reported result | 75success rateReported resultApr 23, 2026 | Not published | 76.2success rateReported resultMay 19, 2026 |
| BrowseCompPublisher-reported result | 82.7accuracyReported resultApr 23, 2026 | 91.5accuracyReported resultSep 3, 2026 | Not published |
| GDPvalPublisher-reported result | 83wins or tiesReported resultApr 23, 2026 | Not published | Not published |
| ARC-AGI-2Verified | 73.3accuracyReported resultApr 23, 2026 | Not published | Not published |
| FrontierMath · Tier 1-3Publisher-reported result | 47.6accuracyReported resultApr 23, 2026 | Not published | Not published |
| FrontierMath · Tier 4Publisher-reported result | 27.1accuracyReported resultApr 23, 2026 | Not published | Not published |
| MMMU Prono tools | 81.2accuracyReported resultApr 23, 2026 | Not published | 80.5accuracyReported resultMay 19, 2026 |
| Agents' Last ExamPublisher-reported result | Not published | 59.3Reported resultSep 3, 2026 | Not published |
| OSWorld 2.0 · V2-Offline (v2026.08.08)Publisher-reported result | Not published | 72.6partial scoreReported resultSep 3, 2026 | Not published |
| ScreenSpot-Prono tools | Not published | 92.7accuracyReported resultSep 3, 2026 | Not published |
| AutomationBenchPublisher-reported result | Not published | 41.4success rateReported resultSep 3, 2026 | Not published |
| BenchCADwith tools | Not published | 95.9geometric overlapReported resultSep 3, 2026 | Not published |
| Terminal-Bench 4.0Publisher-reported result | Not published | 57.9success rateReported resultSep 3, 2026 | Not published |
| DeepSWE 1.1Publisher-reported result | Not published | 74.1resolve rateReported resultSep 3, 2026 | Not published |
| FrontierCode 1.1 · ExtendedPublisher-reported result | Not published | 64.5scoreReported resultSep 3, 2026 | Not published |
| Terminal-Bench Science 0.1Publisher-reported result | Not published | 64.6success rateReported resultSep 3, 2026 | Not published |
| FrontierMath v2 · Tier 4Publisher-reported result | Not published | 97.6accuracyReported resultSep 3, 2026 | Not published |
| ExploitBenchwithout production safeguards | Not published | 100success rateReported resultSep 3, 2026 | Not published |
| SRE-Benchsingle attempt | Not published | 88success rateReported resultSep 3, 2026 | Not published |
| ARC-AGI-3Publisher-reported result | Not published | 99.9RHAEReported resultSep 3, 2026 | Not published |
| Artificial Analysis Intelligence Index 4.1.1max | Not published | 61index scoreReported resultSep 3, 2026 | Not published |
| Artificial Analysis Coding Agent Index 1.4max | Not published | 67index scoreReported resultSep 3, 2026 | Not published |
| SWE-Bench ProPublisher-reported result | Not published | Not published | 54.2resolve rateReported resultMay 28, 2026 |
| Terminal-Bench 2.1Publisher-reported result | Not published | Not published | 70.3success rateReported resultMay 28, 2026 |
| Artificial Analysis Coding Agent Indexhigh | Not published | Not published | 43average pass@1Reported result |
| SWE-Atlas Codebase QnAhigh | Not published | Not published | 45.6pass@1Reported result |
| SWE-Bench Pro · hard-aahigh | Not published | Not published | 15.1pass@1Reported result |
| Terminal-Bench 2.1high | Not published | Not published | 68.3pass@1Reported result |
| Humanity's Last Exam · full set, text + MMPublisher-reported result | Not published | Not published | 44.4accuracyReported resultMay 19, 2026 |
| ARC-AGI-2Publisher-reported result | Not published | Not published | 77.1accuracyReported resultMay 19, 2026 |
| MCP AtlasPublisher-reported result | Not published | Not published | 78.2success rateReported resultMay 19, 2026 |
| CharXiv Reasoningno tools | Not published | Not published | 83.3accuracyReported resultMay 19, 2026 |
| GDPval-AAPublisher-reported result | Not published | Not published | 1314EloReported resultMay 19, 2026 |
| Price per million tokens | |||
| Input | $2.50 | $10.00 | $2.00 (best) |
| Output | $15.00 | $50.00 | $12.00 (best) |
| Cached input | $0.25 | $1.00 | $0.20 (best) |
| Blended (3:1) | $5.63 | $20.00 | $4.50 (best) |
| Long-context rate | Over 272K: $5.00 / $22.50 | Over 272K: $20.00 / $75.00 | Over 200K: $4.00 / $18.00 |
| Price source | Official OpenAI API | Official OpenAI API | Official Google API |
| Limits | |||
| Context window | 1,050,000 tokens (best) | 1,050,000 tokens (best) | 1,048,576 tokens |
| Max input | 922,000 tokens | 922,000 tokens | Not published |
| Max output | 128,000 tokens (best) | 128,000 tokens (best) | 65,536 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | Yes | Yes |
| PDFs | Yes | Yes | Yes |
| Audio | No | No | Yes |
| Video | No | No | Yes |
| Reasoning | Yeslow · medium · high · xhigh | Yeslow · medium · high · xhigh · max | Yeslow · medium · high |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | Yes |
| File attachments | Yes | Yes | Yes |
| Temperature control | Yes | No | Yes |
| Reasoning control | effort | effort | effort |
| Availability | |||
| Weights | Proprietary | Proprietary | Proprietary |
| API model ID | gpt-5.4 | gpt-6-astra | gemini-3.1-pro-preview |
| API providers | 50 | 56 (best) | 40 |
| Released | Mar 5, 2026 | Sep 4, 2026 | Feb 19, 2026 |
| Knowledge cutoff | Aug 31, 2025 | Apr 30, 2026 | Jan 2025 |
| Publisher documentation | Publisher documentation | Publisher documentation | Publisher documentation |
| Source metadata updated | Mar 5, 2026 | Sep 4, 2026 | Feb 19, 2026 |
| Data sources | models.dev · Epoch AI | models.dev · Epoch AI | models.dev · Epoch AI |
| Catalog checked | Nov 22, 2026 | Nov 22, 2026 | Nov 22, 2026 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
GPT-5.4$55.00
GPT-6 Astra$200.00
Gemini 3.1 Pro Preview$44.00
Which should you choose?
Which is better: GPT-5.4, GPT-6 Astra or Gemini 3.1 Pro Preview?
It is close. Our weighted score puts them within 1 points (Gemini 3.1 Pro Preview 68/100, GPT-6 Astra 66/100, GPT-5.4 65/100), so choose by what matters most for your work: GPT-6 Astra for raw capability and Gemini 3.1 Pro Preview on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.GPT-6 Astra is the better all-round choice, scoring 89/100 against Gemini 3.1 Pro Preview (84) and GPT-5.4 (82). It leads on capability. Gemini 3.1 Pro Preview wins on inputs & features. The score weighs capability 67%, inputs & features 20%, context window 13%.
Which is cheaper, GPT-5.4, GPT-6 Astra or Gemini 3.1 Pro Preview?
Gemini 3.1 Pro Preview is cheaper at $2.00 input / $12.00 output per million tokens (official Google API price). GPT-5.4 costs $2.50 input / $15.00 output per million tokens (official OpenAI API price); GPT-6 Astra costs $10.00 input / $50.00 output per million tokens (official OpenAI API price). At a typical mix of three input tokens to one output token, that is $4.50 per million tokens for Gemini 3.1 Pro Preview versus $5.63 for GPT-5.4 (1.3× as much) and $20.00 for GPT-6 Astra (4.4× as much).
Which scores higher on benchmarks?
GPT-6 Astra scores higher on the Capabilities Index (ECI): GPT-6 Astra 169.2 (#4 of 159), GPT-5.4 157.9 (#29 of 159) and Gemini 3.1 Pro Preview 156.3 (#41 of 159). Their confidence ranges do not overlap (166.4–172.5 vs 156.0–160.0), so the gap is a real one. On individual benchmarks: GPQA Diamond — GPT-6 Astra 95.8%, Gemini 3.1 Pro Preview 94.4%, GPT-5.4 93.3%; FrontierMath Tiers 1–3 — GPT-6 Astra 93.7%, GPT-5.4 78.6%, Gemini 3.1 Pro Preview 59.7%; OTIS Mock AIME 2024–2025 — GPT-6 Astra 100%, GPT-5.4 97.8%, Gemini 3.1 Pro Preview 95.6%; SimpleQA Verified — GPT-6 Astra 75.6%, Gemini 3.1 Pro Preview 73.5%, GPT-5.4 45.1%.
Which is better for coding?
There are no published SWE-bench Verified results for GPT-6 Astra yet, so there is no like-for-like coding score. On overall capability, GPT-6 Astra leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.
Which has the bigger context window?
Their context windows are effectively the same size: GPT-5.4 1,050,000, GPT-6 Astra 1,050,000 and Gemini 3.1 Pro Preview 1,048,576 tokens. Maximum output per response: GPT-5.4 up to 128,000, GPT-6 Astra up to 128,000, Gemini 3.1 Pro Preview up to 65,536 tokens.
Which can read images, PDFs, audio or video?
GPT-5.4 accepts text, images and PDFs; GPT-6 Astra accepts text, images and PDFs; Gemini 3.1 Pro Preview accepts text, images, PDFs, audio and video. Gemini 3.1 Pro Preview handles the widest range of inputs.
Are any of these open source?
No. GPT-5.4, GPT-6 Astra and Gemini 3.1 Pro Preview are proprietary and only available through APIs and apps.
Which is newer?
GPT-6 Astra is the newest, released Sep 4, 2026. GPT-5.4 came out Mar 5, 2026; Gemini 3.1 Pro Preview came out Feb 19, 2026. Knowledge cutoff: GPT-5.4 Aug 31, 2025, GPT-6 Astra Apr 30, 2026, Gemini 3.1 Pro Preview Jan 2025.
How do you decide the winner?
This rating uses capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 22, 2026.This rating uses capability (67%, independent benchmark results); inputs & features (20%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (13%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 22, 2026.