EvaOmni
Models answer questions about videos and identify the audio and visual evidence behind their answers. The score accounts for both correctness and evidence timing.
- Made by
- Xiaoxing Hu and colleagues
- Released
- October 2026
- Kind
- Audio understanding and voice
- Level
- Everyday
- Scored
- Checked automatically
- Answers
- Multiple choice
- Tasks
- All public
- Measures
- Capability
- Language
- English
- Interaction
- Single turn
- Refresh
- One fixed set
- Run by
- Anyone
- In views
- Vision, Audio and speech
- Strongest model tested
-
Gemini 4 Argon #10 on the capability index
- Last model added
- September 2026
- Scores refreshed
- November 20th, 2026
Gemini 3.7 Flash leads with 79.4% among models released by September 2026 Gemini 3.7 Flash leads with 79.4% among models released by September 2026
Best score per entry from the benchmark's own leaderboard, read on November 20th, 2026. Where a model ran with several settings or harnesses, we keep its best. Names in gray aren't in our model list: fine-tunes, agent systems, products and older models. They don't count toward leaders. This view shows only models we track, each at its best.
The newest model with a score here came out in September 2026, and nobody has tested a newer one. Among the 20 highest-ranked models on the capability index, these have no score yet:
- GPT-6.2 Astra
- Claude Fable 5.2
-
Gemini 4 Carbon
- GPT-6.1 Terra
- and 15 more
- 79.4
Gemini 3.7 Flash
- 78.0
Gemini 3.8 Flash
- 74.4
Gemini 3.6 Flash
- 72.3
Gemini 3.1 Pro
- 71.0
Gemini 2.5 Pro
- 70.9 Doubao-Seed-2.1-Lite
- 68.5
Gemini 3.5 Flash
- 61.4
Gemini 4 Argon
- 58.2
Qwen3.8-Omni-Flash
- 56.8 MiMo-V2.5
- 55.4
Doubao Seed 2.0 Lite
- 53.6 MiMo-V2.6 Flash
- 51.8 MiMo-V2.6 Pro
- 49.0
Qwen3.5-Omni-Plus
- 48.3
Gemini 3.5 Flash-Lite
- 48.1
Gemini 2.5 Flash
- 47.8
Gemini 3.1 Flash-Lite
- 39.7
Gemini 2.5 Flash-Lite
- 37.7
Qwen3.5-Omni-Flash
- 25.2
Qwen3-Omni-30B-A3B
- 24.8
Qwen3-Omni-30B-A3B-Thinking
- 24.2
Nemotron 3 Nano Omni 30B-A3B
- 16.4
Qwen2.5-Omni-7B
- 1
Gemini 3.7 Flash 79.4%
- 2
Gemini 3.8 Flash 78%
- 3
Gemini 3.6 Flash 74.4%
- 4
Gemini 3.1 Pro 72.3%
- 5
Gemini 2.5 Pro Jun 2025 71%
- 6 Doubao-Seed-2.1-Lite 70.9%
- 7
Gemini 3.5 Flash 68.5%
- 8
Gemini 4 Argon 61.4%
- 9
Qwen3.8-Omni-Flash 58.2%
- 10 MiMo-V2.5 56.8%
- 11
Doubao Seed 2.0 Lite Apr 2026 55.4%
- 12 MiMo-V2.6 Flash 53.6%
- 13 MiMo-V2.6 Pro 51.8%
- 14
Qwen3.5-Omni-Plus 49%
- 15
Gemini 3.5 Flash-Lite 48.3%
- 16
Gemini 2.5 Flash Sep 2025 48.1%
- 17
Gemini 3.1 Flash-Lite 47.8%
- 18
Gemini 2.5 Flash-Lite Sep 2025 39.7%
- 19
Qwen3.5-Omni-Flash 37.7%
- 20
Qwen3-Omni-30B-A3B 25.2%
- 21
Qwen3-Omni-30B-A3B-Thinking 24.8%
- 22
Nemotron 3 Nano Omni 30B-A3B 24.2%
- 23
Qwen2.5-Omni-7B 16.4%
Source: Official EvaOmni leaderboard
- 79.4
Gemini 3.7 Flash
- 78.0
Gemini 3.8 Flash
- 74.4
Gemini 3.6 Flash
- 72.3
Gemini 3.1 Pro
- 71.0
Gemini 2.5 Pro
- 68.5
Gemini 3.5 Flash
- 61.4
Gemini 4 Argon
- 58.2
Qwen3.8-Omni-Flash
- 56.8 MiMo-V2.5
- 55.4
Doubao Seed 2.0 Lite
- 53.6 MiMo-V2.6 Flash
- 51.8 MiMo-V2.6 Pro
- 49.0
Qwen3.5-Omni-Plus
- 48.3
Gemini 3.5 Flash-Lite
- 48.1
Gemini 2.5 Flash
- 47.8
Gemini 3.1 Flash-Lite
- 39.7
Gemini 2.5 Flash-Lite
- 37.7
Qwen3.5-Omni-Flash
- 25.2
Qwen3-Omni-30B-A3B
- 24.8
Qwen3-Omni-30B-A3B-Thinking
- 24.2
Nemotron 3 Nano Omni 30B-A3B
- 16.4
Qwen2.5-Omni-7B
- 1
Gemini 3.7 Flash 79.4%
- 2
Gemini 3.8 Flash 78%
- 3
Gemini 3.6 Flash 74.4%
- 4
Gemini 3.1 Pro 72.3%
- 5
Gemini 2.5 Pro Jun 2025 71%
- 6
Gemini 3.5 Flash 68.5%
- 7
Gemini 4 Argon 61.4%
- 8
Qwen3.8-Omni-Flash 58.2%
- 9 MiMo-V2.5 56.8%
- 10
Doubao Seed 2.0 Lite Apr 2026 55.4%
- 11 MiMo-V2.6 Flash 53.6%
- 12 MiMo-V2.6 Pro 51.8%
- 13
Qwen3.5-Omni-Plus 49%
- 14
Gemini 3.5 Flash-Lite 48.3%
- 15
Gemini 2.5 Flash Sep 2025 48.1%
- 16
Gemini 3.1 Flash-Lite 47.8%
- 17
Gemini 2.5 Flash-Lite Sep 2025 39.7%
- 18
Qwen3.5-Omni-Flash 37.7%
- 19
Qwen3-Omni-30B-A3B 25.2%
- 20
Qwen3-Omni-30B-A3B-Thinking 24.8%
- 21
Nemotron 3 Nano Omni 30B-A3B 24.2%
- 22
Qwen2.5-Omni-7B 16.4%
Source: Official EvaOmni leaderboard
| # | Entry | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 79.4% | Aug 2026 | Official leaderboard | |
| 2 | | 78% | Sep 2026 | Official leaderboard | |
| 3 | | 74.4% | Jul 2026 | Official leaderboard | |
| 4 | | 72.3% | Feb 2026 | Official leaderboard | |
| 5 | | 71% | Jun 2025 | Official leaderboard | |
| 6 | Doubao-Seed-2.1-Lite closed weights | 70.9% | Official leaderboard | ||
| 7 | | 68.5% | May 2026 | Official leaderboard | |
| 8 | | 61.4% | Sep 2026 | Official leaderboard | |
| 9 | | 58.2% | Sep 2026 | Official leaderboard | |
| 10 | MiMo-V2.5 | 56.8% | Apr 2026 | Official leaderboard | |
| 11 | | 55.4% | Apr 2026 | Official leaderboard | |
| 12 | MiMo-V2.6 Flash | 53.6% | Sep 2026 | Official leaderboard | |
| 13 | MiMo-V2.6 Pro | 51.8% | Sep 2026 | Official leaderboard | |
| 14 | | 49% | Mar 2026 | Official leaderboard | |
| 15 | | 48.3% | Jul 2026 | Official leaderboard | |
| 16 | | 48.1% | Sep 2025 | Official leaderboard | |
| 17 | | 47.8% | Mar 2026 | Official leaderboard | |
| 18 | | 39.7% | Sep 2025 | Official leaderboard | |
| 19 | | 37.7% | Mar 2026 | Official leaderboard | |
| 20 | | 25.2% | Sep 2025 | Official leaderboard | |
| 21 | | 24.8% | Sep 2025 | Official leaderboard | |
| 22 | | 24.2% | Apr 2026 | Official leaderboard | |
| 23 | | 16.4% | Mar 2025 | Official leaderboard |
| # | Model | Score | Setting | Date | Source |
|---|---|---|---|---|---|
| 1 | | 79.4% | Aug 2026 | Official leaderboard | |
| 2 | | 78% | Sep 2026 | Official leaderboard | |
| 3 | | 74.4% | Jul 2026 | Official leaderboard | |
| 4 | | 72.3% | Feb 2026 | Official leaderboard | |
| 5 | | 71% | Jun 2025 | Official leaderboard | |
| 6 | | 68.5% | May 2026 | Official leaderboard | |
| 7 | | 61.4% | Sep 2026 | Official leaderboard | |
| 8 | | 58.2% | Sep 2026 | Official leaderboard | |
| 9 | MiMo-V2.5 | 56.8% | Apr 2026 | Official leaderboard | |
| 10 | | 55.4% | Apr 2026 | Official leaderboard | |
| 11 | MiMo-V2.6 Flash | 53.6% | Sep 2026 | Official leaderboard | |
| 12 | MiMo-V2.6 Pro | 51.8% | Sep 2026 | Official leaderboard | |
| 13 | | 49% | Mar 2026 | Official leaderboard | |
| 14 | | 48.3% | Jul 2026 | Official leaderboard | |
| 15 | | 48.1% | Sep 2025 | Official leaderboard | |
| 16 | | 47.8% | Mar 2026 | Official leaderboard | |
| 17 | | 39.7% | Sep 2025 | Official leaderboard | |
| 18 | | 37.7% | Mar 2026 | Official leaderboard | |
| 19 | | 25.2% | Sep 2025 | Official leaderboard | |
| 20 | | 24.8% | Sep 2025 | Official leaderboard | |
| 21 | | 24.2% | Apr 2026 | Official leaderboard | |
| 22 | | 16.4% | Mar 2025 | Official leaderboard |
Rankings by part
We read 3 parts from the benchmark’s own leaderboard: Level 1 · Retrieval & grounding, Level 2 · Basic understanding and Level 3 · Complex reasoning. Each ranks models on one part of the test. Gemini 3.7 Flash leads 2 of them, and Gemini 3.8 Flash leads the other one. Arrows show how far a model moved from its overall rank among the models we track.
Level 1 · Retrieval & grounding
22 models we track have a score here.
- 1
Gemini 3.7 Flash 85.3%
- 2
Gemini 3.8 Flash 83.4%
- 3
Gemini 3.6 Flash 80.9%
- 4
Gemini 2.5 Pro Jun 2025 ↑1 76.5%
- 5
Gemini 3.1 Pro ↓1 74.7%
- 6
Gemini 4 Argon ↑1 67.1%
- 7 MiMo-V2.5 ↑2 65.4%
- 8
Qwen3.8-Omni-Flash 65%
- 9
Gemini 3.5 Flash ↓3 64.1%
- 10 MiMo-V2.6 Flash ↑1 61.3%
Level 2 · Basic understanding
22 models we track have a score here.
- 1
Gemini 3.8 Flash ↑1 73.9%
- 2
Gemini 3.7 Flash ↓1 73.6%
- 3
Gemini 3.5 Flash ↑3 69.5%
- 4
Gemini 3.1 Pro 68.6%
- 5
Gemini 3.6 Flash ↓2 68.4%
- 6
Gemini 2.5 Pro Jun 2025 ↓1 65%
- 7
Doubao Seed 2.0 Lite Apr 2026 ↑3 54.1%
- 8 MiMo-V2.5 ↑1 52.3%
- 9
Qwen3.8-Omni-Flash ↓1 52.3%
- 10
Gemini 4 Argon ↓3 52%
Level 3 · Complex reasoning
22 models we track have a score here.
- 1
Gemini 3.7 Flash 79.1%
- 2
Gemini 3.5 Flash ↑4 77.8%
- 3
Gemini 3.1 Pro ↑1 76.5%
- 4
Gemini 3.8 Flash ↓2 74.5%
- 5
Gemini 3.6 Flash ↓2 73.2%
- 6
Gemini 2.5 Pro Jun 2025 ↓1 72.5%
- 7
Gemini 4 Argon 72.5%
- 8
Doubao Seed 2.0 Lite Apr 2026 ↑2 62.7%
- 9
Qwen3.8-Omni-Flash ↓1 56.2%
- 10 MiMo-V2.6 Pro ↑2 49.7%
Number one over time
Lab claims count from the day the card came out, independent runs from the model’s release.
Source: Official EvaOmni leaderboard
Scores over time
All the scores we have, one dot each, so a model tested at several settings appears more than once.
Source: Official EvaOmni leaderboard
No lab model card reports it yet
We read the headline results of 540 launch posts from 57 labs, and none of them list this benchmark.
More in Audio and video
- Video-MMMU In use 300 expert-level lecture videos with questions testing perception, comprehension and adaptation of knowledge. Accuracy.
Qwen 3.8 Max 88.7%
- LVBench In use Hours-long video understanding with multiple-choice questions on reasoning, grounding and summarization.
Gemini 4 Argon 91.7%
- MMVU In use 3,000 expert-annotated questions on videos across 27 disciplines. Multiple-choice and open-ended accuracy.
Qwen 3.8 Max 82.4%
- MLVU In use Multi-task long video understanding (minutes to hours) with multiple-choice and generation tasks. Accuracy.
Qwen 3.8 Max 90.8%
- FLEURS In use Models transcribe read speech in 102 languages built from FLoRes-101 sentences. Model cards usually report word error rate, so lower scores are better.
Phi-4-multimodal 4.00%
- VoiceBench In use Spoken instructions with speaker, environment and content variation. Voice assistant responses scored by GPT judge or rules.
Qwen3.5-Omni-Plus 93.1%
Data audit
All 10 checks pass. Every benchmark
Catalog record 2 pass
- Pass Task access All tasks are public.
- Pass Confidence Checked against a primary source.
Scores 4 pass 1 note
- Pass Independent runs Scores from the official leaderboard (23 entries).
- Pass Models scored 22 models we track, plus 1 other entry on its leaderboard.
- Pass Newest score The newest is from September 2026, for Gemini 4 Argon.
- Note Frontier models Only 1 of the top 10 has a score. The strongest tested is Gemini 4 Argon (#10).
- Pass Headroom The best is 79.4%, under 85%, so it still separates models.
Leaderboard import 3 pass
- Pass Importer We read the board on xiaoxing2001.github.io: 23 rows for models we track and 1 other entry at the last read.
- Pass Last read November 20th, 2026.
- Pass Read worked The last read worked.
Consistency 1 pass 1 note
- Note Lab claims No model has both a lab number and an independent run.
- Pass Known issues No published audit found problems.