# Lab claims and independent checks

[https://timesof.ai/tracker/lab-claims](https://timesof.ai/tracker/lab-claims)

Rows are added when we publish a launch article that cites a lab claim, and a row changes when a published article records a new check. Last updated Oct 27, 2026.

Each row is one model launch: the lab's headline claim, the independent check one of our articles cites for it, and a plain verdict. Every claim, check, date and link here comes from an article we have already published. Where an article cites no independent check, the row says so.

## Claims and checks

| Lab | Model | Lab's headline claim | Independent check | Verdict | Our article |
| --- | --- | --- | --- | --- | --- |
| OpenAI | GPT-6.1 Terra | [“It says those prices are 50% lower than those of GPT-5.6 Terra and GPT-6.1 Sol.”](https://openai.com/index/introducing-gpt-6-1-terra/) | None cited | Not yet checked | [Oct 27, 2026](https://timesof.ai/2026/10/openai-gpt-6-1-terra-launch-pricing-system-card "OpenAI Prices GPT-6.1 Terra at $1 and $5 per Million Tokens, and Its System Card Reports 29.6% Restriction Workarounds in a Test Without Safeguards") |
| Moonshot AI | Kimi K3.1 Pro | [“Moonshot says K3.1 Pro scored 65.7%, ‘ahead of GPT-6 Astra (58.2%) and narrowly behind Claude Opus 5.5 (66.4%).’”](https://www.kimi.ai/blog/kimi-k3-1-pro) | [Artificial Analysis](https://x.com/i/status/2113688083145314416), Oct 23, 2026: measured 67% on Terminal-Bench 4.0, which it called ‘the highest score of any model’ on that test | Partly | [Oct 24, 2026](https://timesof.ai/2026/10/moonshot-kimi-k3-1-pro-weights-nov-4-cyber-data-removed "Moonshot Resets Kimi K3.1 Pro Quotas After Rate-Limit Complaints as Independent Tests Rank It Fourth") |
| Recursive Superintelligence | Flint | [“Recursive says Flint leads mixture-of-experts models with fewer than 50 billion total parameters on SWE-Bench Pro v2, Terminal-Bench 2.1 and SWE-Bench Verified”](https://recursive.com/updates/introducing-recursive-flint) | None cited | Not yet checked | [Oct 22, 2026](https://timesof.ai/2026/10/recursive-flint-40b-open-weight-laptop-coding-model-apache-2 "Recursive Releases Flint, an Apache-2.0 Open-Weight Coding Model for Laptops That It Says Its Automated-Research System Helped Build") |
| DeepSeek | DeepSeek-V4.1-Flash-1017 | [“DeepSeek reports Humanity's Last Exam without tools at 42.6 vs 36.8; Terminal-Bench 4.0 at 42.3 vs 31.2”](https://huggingface.co/deepseek-ai/DeepSeek-V4.1-Flash-1017) | None cited | Not yet checked | [Oct 20, 2026](https://timesof.ai/2026/10/deepseek-v4-1-flash-1017-open-weights-mit "DeepSeek Releases V4.1-Flash-1017 Open Weights Under MIT; Artificial Analysis Scores It 45.10") |
| Meta | Muse Spark Open | [“the most capable US open-weight model to date”](https://research.meta.ai/blog/muse-spark-open) | None cited | Not yet checked | [Oct 16, 2026](https://timesof.ai/2026/10/meta-muse-spark-open-816b-open-weights "Meta Releases Muse Spark Open Weights: An 816B Mixture-of-Experts Under Attribution and $20M Model-Service Terms") |
| Meta | Muse Wonder and Muse Wonder Full | [“Wonder and Wonder Full reach benchmark scores comparable to Claude Fable 5.1 and GPT-6 Astra”](https://research.meta.ai/blog/muse-wonder) | [Artificial Analysis](https://artificialanalysis.ai/leaderboards/models), Oct 13, 2026: lists Muse Wonder Full (max) at 56 on its Intelligence Index, tied with Claude Sonnet 5.5 (max) and Claude Opus 5.5 (xhigh) | Partly | [Oct 13, 2026](https://timesof.ai/2026/10/meta-muse-wonder-first-frontier-model "Meta Releases Muse Wonder, Its First Frontier Model, and Artificial Analysis Puts It Two Points Off the Top") |
| Anthropic | Claude Haiku 5.5 | [“Anthropic's table puts Haiku 5.5 ahead of Luna on every eval where both are scored and behind Sonnet 5.5.”](https://www.anthropic.com/claude-haiku-5-5) | [Artificial Analysis](https://artificialanalysis.ai/leaderboards/models), Oct 8, 2026: does compare like with like on one composite: Haiku 5.5 (max) 43, GPT-6 Luna (max) 38 | Partly | [Oct 8, 2026](https://timesof.ai/2026/10/anthropic-claude-haiku-5-5-sonnet-cache-cut "Claude Haiku 5.5 Matches GPT-6 Luna's Price on Short Prompts — and Sonnet 5.5's Cache Reads Get Halved") |
| Mistral AI | Mistral Large 4 (preview) | [“is competitive with the strongest open models globally”](https://mistral.ai/news/mistral-large-4/) | [Artificial Analysis](https://artificialanalysis.ai/models/mistral-large-4), Oct 6, 2026: lists Mistral Large 4 Preview at 38 on its Intelligence Index | Doesn't match | [Oct 6, 2026](https://timesof.ai/2026/10/mistral-large-4-preview-1t-open-weights "Mistral Puts 1T-Parameter Large 4 on a Paid Preview API; Weights by Month-End, AA Scores 38") |
| Reflection AI | Beam | [“Reflection says Beam is “approaching Qwen 3.8-Max””](https://reflection.ai/blog/introducing-beam) | None cited | Not yet checked | [Oct 4, 2026](https://timesof.ai/2026/10/reflection-open-weight-imminent "Update: Reflection Shows Beam — 501B / 23B Active, Apache 2.0 Weights Later This Month") |
| Aleph Alpha | Kolibri | [“matches models with up to four times its active parameter count, such as Nemotron 3 Super”](https://aleph-alpha.com/en/blog/kolibri-has-landed-a-sovereign-open-weight-model/) | None cited | Not yet checked | [Oct 3, 2026](https://timesof.ai/2026/10/aleph-alpha-kolibri-open-weight "Aleph Alpha Releases Kolibri: Apache 2.0 German/English MoE, 3.46B Active") |
| Microsoft AI | MAI-Transcribe-2-Streaming | [“Microsoft says it ranks no. 1 for accuracy for both final and partial transcripts on Artificial Analysis”](https://microsoft.ai/news/our-first-streaming-transcription-model/) | None cited | Not yet checked | [Oct 1, 2026](https://timesof.ai/2026/10/microsoft-mai-transcribe-2-streaming "Microsoft Says MAI-Transcribe-2-Streaming Is #1 on Artificial Analysis Streaming Accuracy") |
| OpenAI | GPT-6.1 Sol | [“sold as near GPT-6 Astra on agentic coding, computer use, and professional work at one-fifth of Astra’s standard input and output token prices”](https://openai.com/index/introducing-gpt-6-1-sol) | None cited | Not yet checked | [Sep 29, 2026](https://timesof.ai/2026/09/openai-gpt-61-sol "GPT-6.1 Sol Claims Near-Astra Work at a Fifth of Astra’s Token Price") |
| Anthropic | Claude Sonnet 5.5 | [“fewer tokens mean up to 30% lower cost per task than that predecessor”](https://www.anthropic.com/claude-sonnet-5-5) | [Artificial Analysis](https://artificialanalysis.ai/articles/claude-sonnet-5-5), Sep 28, 2026: Cost per task about $7.60 at that max setting, which AA says is roughly 50% higher than Sonnet 5’s cost per task. | Partly | [Sep 28, 2026](https://timesof.ai/2026/09/anthropic-claude-sonnet-55 "Sonnet 5.5 Nears Opus on the Index — With AA’s Highest Token Usage") |
| Anthropic | Claude Opus 5.5 | [“roughly 40% lower cost than Opus 5 on typical workloads”](https://www.anthropic.com/claude-opus-5-5) | None cited | Not yet checked | [Sep 22, 2026](https://timesof.ai/2026/09/anthropic-claude-opus-5-5 "Claude Opus 5.5 Cuts Prices; Later Independent Tests Measure Different Strengths") |
| xAI | Grok 4.7 | [“twice as fast, at half the price of comparable models”](https://x.ai/news/grok-4-7) | None cited | Not yet checked | [Sep 21, 2026](https://timesof.ai/2026/09/xai-grok-4-7 "Grok 4.7 Holds Grok 4.6 Prices and Moves the Specialty Benches") |
| xAI | Grok Voice Transcribe 2.0 | [“xAI says that on the public Artificial Analysis leaderboard, Transcribe 2.0 ranks first for accuracy among 32 streaming models.”](https://x.ai/news/grok-voice-transcribe-2) | None cited | Not yet checked | [Sep 18, 2026](https://timesof.ai/2026/09/xai-grok-voice-transcribe-2 "Grok Voice Transcribe 2.0 Cuts Short-Phrase Errors; Price Stays Put") |
| Google | Gemini 3.8 Live Extended Thinking | [“Google says Extended Thinking is #1 on Artificial Analysis Speech to Speech Quality Index (82.6)”](https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-8-live-gemini-3-8-live-extended-thinking/) | None cited | Not yet checked | [Sep 15, 2026](https://timesof.ai/2026/09/google-gemini-3-8-live-extended-thinking "Gemini 3.8 Live Claims the Independent Speech-to-Speech Board") |
| OpenAI | GPT-6 Astra | [“calling it the “world’s most intelligent and aligned model””](https://openai.com/index/gpt-6-astra/) | None cited | Not yet checked | [Sep 3, 2026](https://timesof.ai/2026/09/openai-gpt-6-astra "Astra Is Critical Cyber — and Comes With a $1B Defender Subsidy") |
| Meta | Muse Spark 1.3 | [“Meta’s internal coding comparisons report roughly 20% fewer tool calls and 25% fewer tokens than Spark 1.2”](https://research.meta.ai/blog/introducing-muse-spark-1-3) | None cited | Not yet checked | [Sep 2, 2026](https://timesof.ai/2026/09/meta-muse-spark-1-3 "Muse Spark 1.3 Improves Coding Efficiency; Launch Index Trails Fable 5.1") |
| Google | Gemini 3.5 Transcribe | [“Google cites Artificial Analysis WER: 4.0% streaming / 2.6% non-streaming”](https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-5-transcribe/) | None cited | Not yet checked | [Aug 26, 2026](https://timesof.ai/2026/08/google-gemini-3-5-transcribe "Gemini 3.5 Transcribe Brings Speech Recognition Into the Gemini Family") |
| Google | Gemini 3.7 Flash | [“calling it the most intelligent Flash “workhorse” yet for coding and agents”](https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-3-7-flash/) | [Artificial Analysis](https://artificialanalysis.ai/articles/gemini-3-7-time-frontier), Aug 13, 2026: scores 3.7 Flash (high) at 56 on the Intelligence Index (+4 vs 3.6 Flash). | Matches | [Aug 13, 2026](https://timesof.ai/2026/08/google-gemini-3-7-flash "Gemini 3.7 Flash Iterates the Cheap Workhorse — Pro Still Missing") |
| xAI | Grok 4.6 | [“matches GPT-5.6 Sol Max at 61 on the Artificial Analysis Intelligence Index”](https://x.ai/news/grok-4-6) | None cited | Not yet checked | [Aug 12, 2026](https://timesof.ai/2026/08/spacexai-grok-4-6 "xAI’s Grok 4.6 Table Shows a Sol Tie at $2/$6 Token Pricing") |
| xAI | Grok Voice Think Fast 2.0 | [“cites Artificial Analysis leadership on speech-to-speech quality (82.9% vs 79.1% for GPT-Realtime-2.1 High)”](https://x.ai/news/grok-voice-think-fast-2) | None cited | Not yet checked | [Jul 29, 2026](https://timesof.ai/2026/07/spacexai-grok-voice-think-fast-2 "Grok Voice Think Fast 2.0: AA Speech Lead—and an Aug 5 Default Cutover") |
| Anthropic | Claude Opus 5 | [“comes close to Claude Fable 5 frontier intelligence at half the price”](https://www.anthropic.com/news/claude-opus-5) | [Artificial Analysis (BenchLM mirror)](https://benchlm.ai/benchmarks/artificialAnalysis), Jul 24, 2026: Claude Opus 5 \~60.7% — listed ahead of Claude Fable 5 (\~59.9%) and GPT-5.6 Sol (\~58.9%) among \~167 models on that snapshot | Partly | [Jul 24, 2026](https://timesof.ai/2026/07/anthropic-claude-opus-5 "Opus 5: Near-Fable as the Daily Default—AA Snapshot Ahead of Sol") |
| Moonshot AI | Kimi K3 | [“overall performance still trails Claude Fable 5 and GPT-5.6 Sol but beats other tested models across coding, agentic, and multimodal suites”](https://www.kimi.com/blog/kimi-k3) | [Artificial Analysis](https://artificialanalysis.ai/articles/kimi-k3-achieves-3-in-the-artificial-analysis-intelligence-index-comparable-to-opus-4-8-and-gpt-5-5), Jul 17, 2026: 57 — #3 overall; comparable to Opus 4.8 / GPT‑5.5; still behind Fable 5 and GPT‑5.6 Sol | Partly | [Jul 17, 2026](https://timesof.ai/2026/07/moonshot-kimi-k3-open-frontier "Kimi K3: Near-Frontier Open Path—AA #3, Prices Under Sol/Fable") |

## What the verdicts mean

- **Matches.** The independent figure for the same measure agrees with the claim, as the article reads it.
- **Partly.** The check supports only part of the claim, was run at a different setting, or the article reads it both ways.
- **Doesn't match.** The independent figure for the same measure disagrees with the claim, as the article reads it.
- **Not yet checked.** The article cites no independent check of this claim.

## Notes on each verdict

- **GPT-6.1 Terra.** Our article compares the price with two earlier Times of AI reports and finds the output price about 58% lower than GPT-5.6 Terra's, not 50%. It cannot say why. That is our arithmetic, not an independent check. The Artificial Analysis page it cites covers other measures.
- **Kimi K3.1 Pro.** AA's 67% is above Moonshot's 65.7%, and AA calls it the highest of any model where Moonshot's table has it narrowly behind Opus 5.5. The article says AA tested the API model, which may differ from the open-weight version. It cites several AA posts and does not say which one carries this figure.
- **Flint.** The article records that Artificial Analysis's leaderboard did not list Flint when checked at 02:59 UTC on October 22. That is an absence, not a score, so there is no check to cite.
- **DeepSeek-V4.1-Flash-1017.** Artificial Analysis scored the model 45.10 on its Intelligence Index, a different measure. The article says only that index is independent here.
- **Muse Spark Open.** The article calls this Meta's claim. The Artificial Analysis score it prints (39) comes from Meta's own comparison table and sits beside non-US models, so it does not test the claim.
- **Muse Wonder and Muse Wonder Full.** AA puts Wonder Full two points below the top entry, so it is close. The article calls it the only non-Anthropic model in AA's top four, but gives no AA scores for Fable 5.1 or Astra, so the comparison named in the claim is not shown directly.
- **Claude Haiku 5.5.** AA agrees with the direction on one composite at max effort. The article calls Anthropic's table not like-for-like, because the effort levels behind the Luna column are unclear. Haiku's own Terminal-Bench score falls from about 39% at max to about 20% at the default medium setting.
- **Mistral Large 4 (preview).** On AA's index the preview sat well behind the top open models (MiMo-V2.6-Pro 46, GLM-5.3 45, Kimi K3 44). The article says that is not a verdict on the final checkpoint. Mistral's claim also says the model outperforms any U.S. or European open-weight model, which nothing cited tests.
- **Beam.** The article says every benchmark is vendor-reported, the comparison table is vendor-compiled, and TechCrunch notes the claims are not independently verified.
- **Kolibri.** The article calls this Aleph Alpha's own comparison, not an independent audit. A look at the Artificial Analysis and LM Arena boards on the evening of October 4 did not show the model, which the article says is not a quality verdict.
- **MAI-Transcribe-2-Streaming.** Our article saw Artificial Analysis's result only via a 24/7 Wall St. card; not yet confirmed on Artificial Analysis directly.
- **GPT-6.1 Sol.** The article found no third-party leaderboard result for the model on launch day and says “near Astra” rested on OpenAI's own task-level cost curves.
- **Claude Sonnet 5.5.** AA's cost per task, about 50% higher than Sonnet 5's at max effort, points the other way. The article says the two figures are at different effort points and task baskets, so they are not directly comparable. It also notes AA's Terminal-Bench 4.0 run was 64%, not Anthropic's 70.6%, and leaves that gap unresolved.
- **Claude Opus 5.5.** The article adds later Artificial Analysis and Andon Labs checks. They measure an intelligence index and simulated vending profit, not this cost claim.
- **Grok 4.7.** The only independent check the article cites is Andon Labs's Vending-Bench 2, a different measure from this price and speed claim. It says it establishes no Arena or Artificial Analysis score for the model.
- **Grok Voice Transcribe 2.0.** The article attributes the ranking to xAI's account of Artificial Analysis and says it did not verify the live board.
- **Gemini 3.8 Live Extended Thinking.** The article lists the ranking under benchmarks as reported by Google. A correction on October 14 attributed it to Google and did not replace it with a check of the board.
- **GPT-6 Astra.** The article lists the lab's benchmarks as vendor-reported and says an independent LMArena or Artificial Analysis ranking is not verified.
- **Muse Spark 1.3.** Artificial Analysis's September 2 evaluation measured its Intelligence Index and cost per task, which the article says are separate from Meta's coding-efficiency tests.
- **Gemini 3.5 Transcribe.** The article calls the Artificial Analysis score the independent score Google cites, and says it did not inspect the original scorecard.
- **Gemini 3.7 Flash.** The article reads AA's +4 over Gemini 3.6 Flash as supporting the capability claim. It does not test Google's own coding and agent figures.
- **Grok 4.6.** The article attributes the table to xAI and says no separately inspected Artificial Analysis or Arena snapshot is claimed.
- **Grok Voice Think Fast 2.0.** The article lists the Artificial Analysis figure as cited on xAI's launch post. It links the board but gives no reading of it.
- **Claude Opus 5.** The snapshot lists Opus 5 slightly ahead of Fable 5, which fits "comes close". It is a July 24 reading through a third-party mirror of AA's index, and the article says to treat it as dated. It does not test the half-price part of the claim.
- **Kimi K3.** AA ranks K3 third overall, behind Fable 5 and GPT-5.6 Sol, which fits the first half of Moonshot's claim. AA calls it comparable to Opus 4.8 and GPT-5.5 rather than ahead of them, and the check covers one index, not the coding, agentic and multimodal suites Moonshot cites.

## Limits

- A verdict reflects only the check the article cites, at the setting and date it gives. Benchmark pages change, and a later check can differ.
- A check often measures something other than what the lab claimed. The notes say when it does.
- Verdicts are our reading of our own articles. They are not a ruling by the lab or by the checker, and a missing check is not evidence either way.