AI Battle > Rankings > AA-Omniscience Hallucination Rate
MiniMax-M3 by MiniMax leads the AA-Omniscience Hallucination Rate ranking with a score of 0.18. The ranking covers 20 evaluated eval omniscience from a public dataset that AI Battle re-checks daily.
Last updated: . Source: public benchmark datasets and provider pricing, aggregated daily; 20 entries shown.
| # | Entry | Creator | Value | Δ vs #1 |
|---|---|---|---|---|
| 1 | MiniMax-M3 | MiniMax | 0.18 | 0.0% |
| 2 | K2 Horizon 375B A23B | MBZUAI Institute of Foundation Models | 0.26 | 40.3% |
| 3 | GLM-5.3-Flash | Z AI | 0.28 | 50.0% |
| 4 | GLM-5.3 (max) | Z AI | 0.30 | 60.4% |
| 5 | Nemotron 3 Ultra 550B A55B (Reasoning) | NVIDIA | 0.30 | 61.1% |
| 6 | Qwen3.8 27B (xhigh) | Alibaba | 0.30 | 64.4% |
| 7 | Muse Spark 1.3 (max) | Meta | 0.33 | 78.8% |
| 8 | Grok 4.6 (high) | SpaceXAI | 0.34 | 86.1% |
| 9 | Gemini 3.5 Flash-Lite | 0.34 | 86.4% | |
| 10 | Qwen3.8 2.4T A95B | Alibaba | 0.39 | 112.6% |
| 11 | GPT-6 Astra (high) | OpenAI | 0.45 | 142.9% |
| 12 | GPT-6 Astra (medium) | OpenAI | 0.47 | 152.5% |
| 13 | GPT-6 Astra (xhigh) | OpenAI | 0.48 | 162.2% |
| 14 | GPT-6 Astra (max) | OpenAI | 0.51 | 178.6% |
| 15 | Kimi K3 (max) | Kimi | 0.53 | 188.7% |
| 16 | Gemini 3.8 Flash (high) | 0.55 | 199.4% | |
| 17 | Claude Opus 5 (Adaptive Reasoning, Max Effort) | Anthropic | 0.61 | 230.0% |
| 18 | Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) | Anthropic | 0.64 | 245.3% |
| 19 | Inkling (xhigh) | Thinking Machines | 0.68 | 267.2% |
| 20 | Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback) | Anthropic | 0.69 | 273.5% |
Across the 20 numeric entries in this window the median is 0.42 and the mean is 0.43, so the typical entry sits 0.24 above the leader. The window spans 0.18 to 0.69.
10 of 20 entries are at or above the median, and the top three hold 23% of the combined value — read it against the metric below, since a higher number is not "better" for every dataset.
12 creators appear in this window; the three most-represented hold 45% of the entries.
| Creator | Entries | Highest value | Top entry |
|---|---|---|---|
| OpenAI | 4 | 0.51 | GPT-6 Astra (max) |
| Anthropic | 3 | 0.69 | Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback) |
| 2 | 0.55 | Gemini 3.8 Flash (high) | |
| Alibaba | 2 | 0.39 | Qwen3.8 2.4T A95B |
| Z AI | 2 | 0.30 | GLM-5.3 (max) |
| Thinking Machines | 1 | 0.68 | Inkling (xhigh) |
| Kimi | 1 | 0.53 | Kimi K3 (max) |
| SpaceXAI | 1 | 0.34 | Grok 4.6 (high) |
| Meta | 1 | 0.33 | Muse Spark 1.3 (max) |
| NVIDIA | 1 | 0.30 | Nemotron 3 Ultra 550B A55B (Reasoning) |
| MBZUAI Institute of Foundation Models | 1 | 0.26 | K2 Horizon 375B A23B |
| MiniMax | 1 | 0.18 | MiniMax-M3 |
The same models are measured across multiple independent datasets. Aggregating the 20 entries above against every other AI Battle dataset gives this cross-section, computed by AI Battle and published nowhere upstream:
| Model | Datasets | Best placements elsewhere |
|---|---|---|
| MiniMax-M3 | 57 | #1/20 in 𝜏³-Banking: Output Tokens per Task, #4/20 in Pricing: Cache Hit, Input, and Output, #4/20 in Pricing: Cache Hit, Input, and Output |
| K2 Horizon 375B A23B | 24 | #8/20 in AA-Briefcase Tool Calls Breakdown, Avg per Task, #12/20 in AA-Omniscience Index: Token Usage, #9/14 in Model Size: Total and Active Parameters |
| GLM-5.3-Flash | 54 | #1/20 in Pricing: Cache Hit, Input, and Output, #1/20 in Pricing: Cache Hit, Input, and Output, #1/20 in AA-Omniscience Index: Cost Breakdown |
| GLM-5.3 (max) | 57 | #3/20 in AA-Briefcase Tool Calls Breakdown, Avg per Task, #4/20 in GDPval-AA v2 Leaderboard, #4/20 in Mean Turns per Task |
| Nemotron 3 Ultra 550B A55B (Reasoning) | 46 | #1/12 in Artificial Analysis Openness Index: Score, #1/12 in Artificial Analysis Openness Index: Components, #2/20 in 𝜏³-Banking: Time per Task |
| Qwen3.8 27B (xhigh) | 43 | #6/20 in 𝜏³-Banking: Score, #8/20 in AA-LCR v1.1: Cost per Task, #8/19 in MMMU-Pro: Total Cost to Run |
| Muse Spark 1.3 (max) | 61 | #3/20 in AA-Briefcase Elo, #3/20 in Output Speed, #3/20 in GDPval-AA v2 Leaderboard |
| Grok 4.6 (high) | 61 | #2/20 in 𝜏³-Banking: Score, #5/20 in AA-Briefcase Elo, #5/20 in AA-Omniscience Index |
| Gemini 3.5 Flash-Lite | 44 | #1/20 in End-to-End Response Time, #1/20 in Output Speed, #1/20 in Time per Intelligence Index Task |
| Qwen3.8 2.4T A95B | 43 | #2/14 in Model Size: Total and Active Parameters, #5/20 in AA-Briefcase Tool Calls Breakdown, Avg per Task, #5/20 in 𝜏³-Banking: Score |
| GPT-6 Astra (high) | 12 | #1/20 in AA-Omniscience Index: Score, #2/19 in MMMU-Pro: Token Usage, #2/19 in MMMU-Pro: Score |
| GPT-6 Astra (medium) | 12 | #1/20 in AA-Omniscience Index: Token Usage, #1/19 in MMMU-Pro: Token Usage, #2/20 in Terminal-Bench v4.0: Output Tokens per Task |
| GPT-6 Astra (xhigh) | 15 | #1/20 in Terminal-Bench v4.0: Score, #2/20 in Humanity's Last Exam: Output Tokens per Task, #3/20 in AA-Omniscience Index: Score |
| GPT-6 Astra (max) | 51 | #1/19 in MMMU-Pro: Score, #2/20 in AA-Omniscience Index, #2/20 in Artificial Analysis Intelligence Index by Open Weights / Proprietary |
| Kimi K3 (max) | 60 | #1/20 in Context Window, #1/20 in AA-LCR v1.1: Score, #1/14 in Model Size: Total and Active Parameters |
| Gemini 3.8 Flash (high) | 60 | #1/11 in Speed, #1/11 in Speed, #2/20 in Output Speed |
| Claude Opus 5 (Adaptive Reasoning, Max Effort) | 44 | #2/20 in AA-Briefcase Elo, #2/20 in GDPval-AA v2 Leaderboard, #2/20 in AA-Briefcase Elo |
| Claude Fable 5 (Adaptive Reasoning, Max Effort, Opus 4.8 Fallback) | 40 | #2/20 in SciCode: Score, #3/20 in AA-Omniscience Index, #3/20 in AA-Omniscience Index |
| Inkling (xhigh) | 52 | #3/20 in Context Window, #3/20 in 𝜏³-Banking: Output Tokens per Task, #5/20 in AA-Briefcase Output Tokens per Task |
| Claude Fable 5.1 (Adaptive Reasoning, High Effort, Default Fallback) | 22 | #1/20 in SciCode: Output Tokens per Task, #2/20 in AA-Omniscience Index: Token Usage, #2/20 in AA-LCR v1.1: Output Tokens per Task |
This ranking carries the metric
omniscienceHallucinationRate from the
AA-Omniscience Hallucination Rate dataset in the tab::eval-omniscience family. Units and the
direction of "better" are not declared by the source dataset, so AI Battle does not invent
them: values are shown exactly as published, and the ordering is the source dataset's own.
Rebuilt on from the
public dataset AA-Omniscience Hallucination Rate (family tab::eval-omniscience).
The source lists 20 entries and all 20 are shown here. AI Battle requests
the dataset's rows, keeps the ordering the source publishes, and computes only the statistics
on this page: median, mean, spread, the #1–#2 gap, the creator breakdown and the raw-data file.
Nothing on this page is generated text about the entries — the numbers come from the source.
Refresh cadence: every deploy re-pulls the dataset, so this page tracks the source's own update cycle. Corrections: see the methodology page.
Machine-readable copy of this table, with the statistics below and the source provenance: /data/rankings/eval-omniscience-aa-omniscience-hallucination-rate.json. Free to reuse with attribution to AI Battle and the source dataset.
MiniMax-M3 by MiniMax currently leads the AA-Omniscience Hallucination Rate ranking with a score of 0.18, the highest value in this dataset across eval omniscience. AI Battle aggregates the dataset from its public source and re-checks it daily.
The AA-Omniscience Hallucination Rate ranking is rebuilt daily from the upstream public dataset. Scores are the source dataset's own published values, so positions track whatever that source last released — each ranking page names the dataset it comes from.
The top 3 are: 1. MiniMax-M3 (0.18), 2. K2 Horizon 375B A23B (0.26), 3. GLM-5.3-Flash (0.28).