Data as of October 26, 2026 · How the score is built
Released Oct 26, 20261.05M contextOpenAI GPT-6.1 Terra model documentation
GPT-6.1 Terra
Decision readingGPT-6.1 Terra scores 75.9 out of 100 and ranks #10 of 229. This profile shows 12 source-displayable benchmark rows; its strongest eligible category is Multimodal & Grounded at #4. API pricing is $1 input and $5 output per million tokens, with cached input at $0.05.
Released Oct 26, 2026 — see all recent releases
Decision snapshot
Each value carries a field reference instead of floating alone. Markers compare this model with the current ranked and priced catalog; they are not absolute quality thresholds.
Capability
75.9/100
field median 50.1#10 of 229 ranked models
Public
#10of 229
Verified —
Price
$1input / $5 output
input median $0.75cached $0.050 · blended $3
Speed
Not measured
field median 96 tok/sTime to first token not measured
Context
1.05Mtokens
field median 256,000Maximum output length is tracked separately
Strongest published evidence
Multimodal & Grounded ranks #4. Particularly strong for screenshots, documents, charts, and grounded multimodal workflows.
Validate before choosing
12 published rows leave some tracked benchmark slots empty. Independent runtime speed has not been measured.
Source-linked · 12 displayable benchmark rows
Category score record
Scores and ranks appear only where published evidence can be displayed. The table keeps the score, weight, cohort, and evidence state together.
| Category | Score | Rank | Percentile | Weight | Benchmarks | Evidence |
|---|---|---|---|---|---|---|
| AgenticRank #8 of 133Percentile 95thWeight 22%4 benchmarksVerified | 72.4 | 4 benchmarks | Verified | |||
| CodingWeight 20%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| ReasoningWeight 17%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MultimodalRank #4 of 58Percentile 95thWeight 12%1 benchmarkVerified | 91.6 | 1 benchmark | Verified | |||
| KnowledgeRank #12 of 188Percentile 94thWeight 12%5 benchmarksVerified | 74.9 | 5 benchmarks | Verified | |||
| MultilingualWeight 7%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| Inst. FollowingWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured | |||
| MathWeight 5%0 benchmarksNot measured | Not measured | 0 benchmarks | Not measured |
12 of 768 tracked benchmark slots have displayable evidence · bars run 0–100
Coverage detailsHow much of this is verified
Coverage is split by category so a strong number never hides a thin evidence base. Verified means the row is tied to a published source; provisional rows remain visible but separate.
- Agentic4/4 verified
- CodingNot measured
- ReasoningNot measured
- Multimodal1/1 verified
- Knowledge5/5 verified
- MultilingualNot measured
- Inst. FollowingNot measured
- MathNot measured
Capability shape
Each axis shows percentile within that category’s eligible cohort. The comparison outline is the median of the six nearest public-score peers; a collapsed vertex means the category is not rank-eligible.
GPT-6.1 Terra category percentile values
- Agentic95th percentile
- CodingNot eligible
- ReasoningNot eligible
- Multimodal95th percentile
- Knowledge94th percentile
- MultilingualNot eligible
- Instruction followingNot eligible
- MathNot eligible
The dashed outline is median of 6 nearest peers.
Eligible category ranks
- Agentic#8/133
- CodingNot ranked
- ReasoningNot ranked
- Multimodal#4/58
- Knowledge#12/188
- MultilingualNot ranked
- Inst. FollowingNot ranked
- MathNot ranked
Benchmark ledger
Agentic opens by default. The marker compares each value with the best source-verified result in the catalog; provisional leaders do not set the reference. Expand the remaining categories for every published row.
Agentic4 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| Terminal-Bench 4.0 | Score50.30% | Versus best verified row Best verified: Claude Sonnet 5.5 · 70.60% | Gap20.3 behind | Weight8% ref. weight | Provider exact |
| Agents' Last Exam | Score60.0% | Versus best verified row Best verified: GPT-6.1 Terra · 60.0% | GapBest verified | Weight3% ref. weight | Provider exact |
| Terminal-Bench-Science 0.1 | Score58.3% | Versus best verified row Best verified: GPT-6 Astra · 64.6% | Gap6.3 behind | WeightDisplay only | Provider exact |
| OSWorld 2.1 OfflineOSWorld 2.1 offline subset (82 tasks) | Score74.2% | Versus best verified row Best verified: Claude Opus 5.5 · 87.2% | Gap13 behind | WeightDisplay only | Provider exact |
Multimodal1 row
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| MMMU-ProMassive Multi-discipline Multimodal Understanding Pro | Score85.5% | Versus best verified row Best verified: GPT-6.1 Terra · 85.5% | GapBest verified | WeightWeighted 40% | Provider exact |
Knowledge5 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| HealthBench (raw)HealthBench raw score | Score51.1% | Versus best verified row Best verified: Claude Sonnet 5.5 · 69.4% | Gap18.3 behind | WeightDisplay only | Provider exact |
| HealthBench (length-adjusted)HealthBench length-adjusted score | Score55.1% | Versus best verified row Best verified: Claude Sonnet 5.5 · 65.4% | Gap10.3 behind | WeightDisplay only | Provider exact |
| HealthBench Professional | Score62.7% | Versus best verified row Best verified: Claude Sonnet 5.5 · 69.2% | Gap6.5 behind | WeightDisplay only | Provider exact |
| HealthBench Professional (raw)HealthBench Professional raw score | Score64.2% | Versus best verified row Best verified: Claude Sonnet 5.5 · 77.1% | Gap12.9 behind | WeightDisplay only | Provider exact |
| HealthBench Hard | Score31.4% | Versus best verified row Best verified: Muse Spark · 42.8% | Gap11.4 behind | WeightDisplay only | Provider exact |
External signals2 rows
| Benchmark | Score | Versus best verified row | Gap | Weight | Evidence |
|---|---|---|---|---|---|
| ExploitBenchExploitBench v8-bench | Score97% | Versus best verified row Best verified: GPT-6 Astra · 100% | Gap2.9 behind | WeightDisplay only | Provider exact |
| SEC-Bench Pro | Score83.3% | Versus best verified row Best verified: GPT-6 Astra · 85.4% | Gap2.1 behind | WeightDisplay only | Provider exact |
What it costs to get this score
Published API price against the public score. The x-axis uses a log scale; the dashed path marks models that are not beaten by a cheaper, higher-scoring option. Price uses average of published input and output rates.
GPT-6.1 Terra · 75.9 score · $3 blended per million tokens
The chart opens on the current model. Scroll horizontally to inspect the full price axis.
Horizontal: blended price per million tokens, log scale · Vertical: public score
Lineage
The sequence follows explicit supersedes links. Each score is estimated for that model; a relative can inform a sparse estimate but never sets a floor, so a newer release can score below an earlier one. Scores and prices remain blank when the corresponding public row or first-party rate is unavailable.
terra-6-1 · terra-6-1
GPT-6 AstraGPT-6 Astra · 84.3GPT-6.1 Sol · 84.3GPT-6 Sol · 78.8GPT-6 Luna · 66.4Spec sheet
Each documented value carries its source. Missing fields stay visible as not sourced or not published, rather than disappearing from the page.
- API model ID
- gpt-6.1-terraOpenAI GPT-6.1 Terra model documentation
- Context window
- 1.05MOpenAI GPT-6.1 Terra model documentation
- Maximum output
- 128,000 tokens (922,000 maximum input tokens)OpenAI GPT-6.1 Terra model documentation
- Knowledge cutoff
- June 1, 2026OpenAI GPT-6.1 Terra model documentation
- Input modalities
- text, imageOpenAI GPT-6.1 Terra model documentation
- Output modalities
- textOpenAI GPT-6.1 Terra model documentation
- Parameters
- Not disclosed by the provider
- Availability
- OpenAI Responses API · OpenAI Chat Completions API · ChatGPT Work · CodexOpenAI GPT-6.1 Terra model documentation
Use the Responses API for tool calling. Chat Completions supports GPT-6.1 Terra without tool calling. OpenAI GPT-6.1 Terra model documentation, read Oct 26, 2026
- Cloud regions
- Not tracked yet
- Lifecycle
- activeOpenAI GPT-6.1 Terra model documentation
- API capabilities
- Streaming · function calling · structured outputs · web/file search · image generation · code interpreter · hosted shell · apply patch · skills · computer use · MCP · tool searchOpenAI GPT-6.1 Terra model documentation
- Prompt caching
- Published at $0.050 per million cached input tokensOpenAI GPT-6.1 Terra model documentation
- Self-host
- Weights are not published
- Rate limits
- Build: 5K RPM / 1M TPM; Grow: 15K RPM / 40M TPM; Free unsupportedOpenAI GPT-6.1 Terra model documentation
How to read this profile
The visual layer above carries the decisions. These notes preserve the model, ranking, coverage, and family context behind the numbers.
GPT-6.1 Terra ranks #10 of 229 on the public leaderboard with a score of 75.87/100. It does not yet have enough sourced coverage for a verified position.
GPT-6.1 Terra is a proprietary model with a 1.05M context window. It uses an explicit reasoning mode, which can improve complex problem solving while adding latency and token use.
Released October 26, 2026 in ChatGPT Work and Codex for Plus, Pro, Enterprise, and Edu users, and in the OpenAI API as gpt-6.1-terra on Responses, Chat Completions, Realtime, Batch, and other endpoints. Tool calling requires the Responses API, where web search, file search, code interpreter, hosted shell, computer use, MCP, and tool search are supported. Fine-tuning is not supported, and the Free usage tier has no access.
OpenAI's October 26, 2026 launch charts report exact Agents' Last Exam v1, MMMU-Pro (Vision), Terminal-Bench 4.0, and Terminal-Bench-Science 0.1 results. We use Max effort for the canonical row, matching earlier GPT-6 intakes. The system card addendum adds raw and length-adjusted HealthBench results, ExploitBench, and SEC-Bench Pro. OpenAI's 74.2% on the OSWorld 2.1 offline set is stored on the separate OSWorld 2.1 Offline lane, not the OSWorld 2.0 lane. The internal factual-error-rate evaluation (4.3% at Max), HealthBench Consensus, MentalHealthBench, the ExploitBench internal port, and other internal safety evaluations remain in the cited sources because they have no matching field. These are provider-run results; the cyber scores are display-only.
GPT-6.1 Terra sits in the GPT-6 family with GPT-6 Astra, GPT-6.1 Sol, GPT-6 Sol, GPT-6 Luna. Its explicit predecessor is GPT-5.6 Terra. 12 of 768 tracked benchmark slots currently have displayable evidence. Missing categories stay blank.
Its strongest eligible category is Multimodal & Grounded at #4, while its lowest eligible position is Knowledge at #12. particularly strong for screenshots, documents, charts, and grounded multimodal workflows.
Last updated October 26, 2026. Runtime fields remain blank until a sourced snapshot exists.
Questions
How does GPT-6.1 Terra perform overall in AI benchmarks?
GPT-6.1 Terra ranks #10 out of 229 models on the public BenchAlign leaderboard, with a score of 75.87/100. Its evidence status is Estimated, and this profile shows 12 source-displayable benchmark rows. The label describes evidence depth, not a provider quality claim; inspect category rows before choosing a workload.
Is GPT-6.1 Terra good for knowledge and understanding?
GPT-6.1 Terra ranks #12 out of 188 eligible models for knowledge and understanding, with a public category score of 74.9/100. Higher-ranked alternatives are available for workloads where this category decides the choice. Check the underlying rows before treating the aggregate as a workload guarantee.
Is GPT-6.1 Terra good for agentic tool use and computer tasks?
GPT-6.1 Terra ranks #8 out of 133 eligible models for agentic tool use and computer tasks, with a public category score of 72.4/100. That places it in the current top ten for this category. Check the underlying rows before treating the aggregate as a workload guarantee.
Is GPT-6.1 Terra good for multimodal and grounded tasks?
GPT-6.1 Terra ranks #4 out of 58 eligible models for multimodal and grounded tasks, with a public category score of 91.6/100. That places it in the current top ten for this category. Check the underlying rows before treating the aggregate as a workload guarantee.
Which sibling models are related to GPT-6.1 Terra?
GPT-6.1 Terra belongs to the GPT-6 family. Related tracked variants include GPT-6 Astra, GPT-6.1 Sol, GPT-6 Sol, plus 1 more. A sibling link indicates shared lineage or a documented configuration relationship; it does not mean the variants have identical pricing, context limits, benchmark evidence, or deployment behavior. Compare before switching.
Does GPT-6.1 Terra have full benchmark coverage on BenchLM?
No. GPT-6.1 Terra currently has 26 source-displayable rows. The profile exposes published, non-generated evidence and leaves missing categories blank until an exact evaluation is available. Coverage describes how much was measured; it is not a penalty added to an individual benchmark result.
What is the context window size of GPT-6.1 Terra?
GPT-6.1 Terra has a documented context window of 1.05M. That figure is the maximum combined prompt and retained-conversation space reported for this exact model; it is not the maximum output length. The profile keeps output limits separate because providers often publish those limits independently.