TAO Synergies · Nasdaq: TAOX Powered by Bittensor
TAO-1
TAO-1 is a frontier-level AI system powered by Bittensor. In our October 2026 runs against seven leading models, it placed #1 on AutomationBench (ahead of Claude Opus 5.5, ChatGPT Astra, and Kimi K3.1), tied for #1 on AA-Omniscience with Claude Opus 5.5, and MATH-500, and scored ahead of Kimi K3.1 on TerminalBench and was #1 on SimpleQA. The API is open: get a key and start in two lines.
Updated
Pricing
Chat: free. New accounts get $5 of credits for Code and Video Studio. Code and API: $0.40 / $1.95 per million input / output tokens.
| Price per million tokens | Input | Output |
|---|---|---|
TAO-1 tao-1 | $0.40 | $1.95 |
| Claude Fable 5.1 | $10.00 | $50.00 |
| GPT-6 Astra | $10.00 | $50.00 |
| Claude Opus 5.5 | $4.00 | $20.00 |
| Kimi K3.1 Pro | $2.00 | $10.00 |
TAO-1: $0.40 / M input · $0.12 / M cached input · $1.95 / M output. TAO-1 Fast costs $0.25 / M input, $0.075 / M cached input and $1.20 / M output; TAO-1 Best is coming soon. OpenAI-compatible API.
Other models: each provider's published standard API price per million tokens, read Oct 26, 2026, before cached-input, batch or other discounts: Anthropic for Claude Fable 5.1 and Claude Opus 5.5 (anthropic.com/pricing), OpenAI for GPT-6 Astra (platform.openai.com/docs/pricing), Moonshot AI for Kimi K3.1 Pro (platform.kimi.ai/docs/pricing/chat).
How does TAO-1 compare with the best models?
| Benchmark | TAO-1 | Best rival | Ahead of | Where TAO-1 stands |
|---|---|---|---|---|
| AA-OMNISCIENCE600 public questions; knowledge index, −100 to 100. Our run (Oct 26), not Artificial Analysis’s own Intelligence Index | 62.7Oct 26 version | 62.0Claude Opus 5.5Next: 58.3 GPT-6 Astra, GPT-6.1 Sol | 58.3GPT-6 Astra, GPT-6.1 Sol | Tied #1 of 8 |
| AUTOMATIONBENCHfirst 100 public AutomationBench 1.0.6 tasks, one run each | 75.0%agent setup | 69.0%Kimi K3.1 ProPublished, different task set: GPT-6 Astra 41.4%, Claude Fable 5.1 31.4% | 69.0%Kimi K3.1 Pro | Ahead of Kimi K3.1 |
| TERMINALBENCHTerminalBench 4.0; the tasks both models completed, one run, 90-minute limit per task | 64.3%TAO-1 Max | 42.9%Kimi K3.1 Pro (our run)Published, different harness and full task set: Claude Opus 5.5 64.9%, GPT-6 Astra 58.2% | 42.9%Kimi K3.1 Pro | Ahead of Kimi K3.1 |
| SIMPLEQA500 factual questions; TAO-1 with web search, the rivals without | 84.4%Oct 26 version | 72.2%GPT-6 Astra, GPT-6.1 SolNext: 67.0% Claude Opus 5.5 | 72.2%GPT-6 Astra, GPT-6.1 Sol | #1 of 8 |
| MATH-500500 competition math problems, strict grading | 98.6%Oct 26 version | 99.4%Claude Opus 5.5Next: 98.6% Gemini 4 Argon | 94.8%GPT-6 Astra | Tied #1 of 9 |
| GPQA DIAMOND198 graduate-level science questions, one attempt each | 95.5%Oct 26 version | 96.5%Gemini 4 ArgonNext: 95.5% GPT-6 Astra, GPT-6.1 Sol | 93.4%Kimi K3.1 | 2nd of 9 |
| IFEVAL200 prompts, strict prompt-level scoring | 95.8%average of 2 runs | 97.0%GPT-6 AstraNext: 95.5% Kimi K3.1Published: no IFEval score found for Claude Fable 5.1 or GPT-6.1 Sol | 93.0%Claude Opus 5.5 | Tied 2nd of 8 |
Methods and raw files
How we measured: TAO-1 numbers are our runs through the public tao-1 API with default settings on Oct 26, 2026 (IFEval: the average of two runs on the same 200 prompts, Oct 25 and Oct 26; SimpleQA rows span several API versions that day), except AutomationBench and TerminalBench, which were measured with TAO-1's agent setup in our harness. Rival numbers are our runs through each model's API on the same items with the same grader, unless marked "published": Kimi K3.1, GPT-6 Astra, GPT-6.1 Sol, Claude Sonnet 5.5, Claude Opus 5.5, DeepSeek 1017 and Mistral Large 4, plus Gemini 4 Argon on GPQA Diamond and MATH-500. A row is a tie when the two scores are within 1 point. "Ahead of" shows the highest-scoring of GPT-6 Astra, GPT-6.1 Sol, Claude Opus 5.5, Gemini 4 Argon and Kimi K3.1 that TAO-1 beats by more than 1 point on the same items (— when none; Claude Fable 5.1 was not run by us). AA-Omniscience: graded with AA's grader (GPT-5.6 Luna, AA's template) on Oct 26, before Artificial Analysis released Intelligence Index v5 on Oct 28; AA's own published index uses its full question set (v5 is now mostly private datasets) and is not comparable. SimpleQA: TAO-1 used web search, the rivals did not. IFEval: Kimi K3.1 (95.5%), GPT-6.1 Sol (95.0%) and DeepSeek 1017 (95.0%) are within 1 point of TAO-1; we found no published IFEval score for Claude Fable 5.1 or GPT-6.1 Sol (BenchLM's IFEval leaderboard and model pages, read Oct 26, 2026). TerminalBench 4.0: both models ran the same 20 pre-selected tasks with a 90-minute limit per task (TerminalBench's standard limit is 8 hours); Kimi K3.1 Pro, in the standard Mini-SWE-agent harness, completed 14 before the run was stopped early, and the row compares the two on those 14; on all 20 tasks TAO-1 Max scored 60.0%; 75% of TAO-1 Max's passes reproduced on a rerun, and a 3-attempt run is in progress. The published TerminalBench scores are the Terminal-Bench 4.0 leaderboard snapshot of Oct 25, 2026 (tbench.ai, mirrored by BenchLM): Claude Opus 5.5 64.85% in Claude Code and GPT-6 Astra 58.18% in Codex, at maximum reasoning, on the full task set with standard limits. Raw results (path, md5): AA-Omniscience bench_finish_2026-10-26/AA_live_1026_2005_600_rows.jsonl da7946f557e62d2156fb52e00dbe32c2 (field grade_luna), Claude Opus 5.5 leaderboard_2026-10-26/runs/opus/omni_full/rows.jsonl ff752c34740398d96512e33e745b0ff1; SimpleQA bench_finish_2026-10-26/simpleqa_live_1026_2005/rows.jsonl a51700993c410b8939e5d652ef5d83a7; MATH-500 math500_live_1026_2005_math 6a610eca86c2e6eb23a0333d06ef7494, Gemini 4 Argon 5e593dab61708e90c59df0ad6a948820; GPQA Diamond suites_tao1_vs_k31_2026-10-25/exam3_gpqa_v12/rows.jsonl 595eaa94cbd752e6d0646f61df36ba98, Gemini 4 Argon runs/argon/gpqa_full d042df94fc1293e08e3f082357593b0b; IFEval ifeval200_live_1026_2005 a7356ca115eb5edf80f292c81e9c2a2c and suites_tao1_vs_k31_2026-10-25/full_ifeval200_tao1/rows.jsonl bf6377e0bc8cf727faac03936e18e3ee; all rivals leaderboard_2026-10-26/FINAL_TABLE.md a4fc511550472a235ac6b38c58fd8792; AutomationBench run 1 ab6d708a37c9b2b660d376852e0d934f (75), run 2 bec16a6c92c6b9a869dacab1650b88a6 (74), Kimi K3.1 Pro 63e3dbd7dd02742518fb500466bd5d3e; TerminalBench handover/TB_K31_TBRULES_vs_MINISWE_v2_20of20_2026-10-26.json e3995f37c8a7175ecd15474993eef88e.
Web Builds: TAO-1 Gallery sites next to Claude Fable 5.1 · Earlier results (Oct 2026)