Gemini 3 Pro Preview (High)
91.7%
no interval published
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,310
- Last sync
- 39 min39 minutes ago
All sources syncing normally
- Arena · Text· 5 hours ago
- Arena · WebDev· 5 hours ago
- Arena · Vision· 5 hours ago
- Arena · Agent· 5 hours ago
- GPQA Diamond· 39 minutes ago
- SWE-bench· 39 minutes ago
- Terminal-Bench· 39 minutes ago
- ARC-AGI-2· 39 minutes ago
Filter by org:
Released:
Gemini 3 Flash Preview (Reasoning)
90.8%
no interval published
DeepSeek V3.2 Speciale
89.6%
no interval published
One grid, every column. Pick axes in the Axes panel — one axis ranks like a single board, several blend into a weighted composite, all of them read as the index. Rank is assigned before any filter and never renumbers.
| Model | Org | ± CI | Swing | Add to compare | |||||
|---|---|---|---|---|---|---|---|---|---|
| 1 | Gemini 3 Pro Preview (High) | — | — | 91.7% | — | #19–120 | |||
| 2 | Gemini 3 Flash Preview (Reasoning) | — | $0.50 / $3 | 90.8% | — | #27–99 | |||
| 3 | DeepSeek V3.2 Speciale | deepseek | — | — | 89.6% | — | — | ||
| 4 | GLM-4.7 (Reasoning) | zai | Dec 2025 | $0.54 / $1.98 | 89.4% | — | #82–189 | ||
| 5 | GPT-5.2 (Medium) | openai | Dec 2025 | $1.75 / $14 | 89.4% | — | #34–92 | ||
| 6 | gpt-oss-120b (High) | openai | Aug 2025 | $0.15 / $0.60 | 87.8% | — | #137–464 | ||
| 7 | Claude Opus 4.5 (Reasoning) | anthropic | Nov 2025 | $5 / $25 | 87.1% | — | #20–62 | ||
| 8 | GPT-5.1 (High) | openai | Nov 2025 | $1.25 / $10 | 86.8% | — | #45–242 | ||
| 9 | MiMo-V2-Flash (Reasoning) | xiaomi | Dec 2025 | — | 86.8% | — | #120–321 | ||
| 10 | DeepSeek V3.2 (Reasoning) | deepseek | Dec 2025 | $0.28 / $0.42 | 86.2% | — | #86–247 | ||
| 11 | o4-mini (High) | openai | Apr 2025 | $1.10 / $4.40 | 85.9% | — | #129–274 | ||
| 12 | Kimi K2 Thinking | kimi | Nov 2025 | $0.60 / $2.50 | 85.3% | — | #35–209 | ||
| 13 | GPT-5.1 Codex (High) | openai | Oct 2026 | $1.25 / $10 | 84.9% | — | #52–375 | ||
| 14 | GPT-5 (High) | openai | Aug 2025 | $1.25 / $10 | 84.6% | — | #64–149 | ||
| 15 | GPT-5 Codex (High) | openai | — | — | 84.0% | — | #17–142 | ||
| 16 | GPT-5 mini (High) | openai | Aug 2025 | $0.25 / $2 | 83.8% | — | #126–343 | ||
| 17 | GPT-5.1 Codex mini (High) | openai | Oct 2026 | $0.25 / $2 | 83.6% | — | #54–425 | ||
| 18 | Grok 4 Fast (Reasoning) | xai | Sep 2025 | — | 83.2% | — | #155–477 | ||
| 19 | MiniMax-M2 | minimax | Oct 2025 | $0.26 / $1.02 | 82.6% | — | #135–415 | ||
| 20 | Grok 4.1 Fast (Reasoning) | xai | Oct 2026 | — | 82.2% | — | #138–429 | ||
| 21 | Grok 4 | xai | — | — | 81.9% | — | — | ||
| 22 | ERNIE 5.0 Thinking Preview | baidu | — | — | 81.2% | — | — | ||
| 23 | MiniMax-M2.1 | minimax | Dec 2025 | $0.30 / $1.20 | 81.0% | — | #34–201 | ||
| 24 | o3 | openai | Apr 2025 | $2 / $8 | 80.8% | — | #79–318 | ||
| 25 | Apriel-v1.6-15B-Thinker | servicenow | — | — | 80.7% | — | — | ||
| 26 | Gemini 2.5 Pro | Jun 2025 | $1.25 / $10 | 80.1% | — | #60–432 | |||
| 27 | DeepSeek V3.1 Terminus (Reasoning) | deepseek | Sep 2025 | $0.27 / $1 | 79.8% | — | #55–168 | ||
| 28 | DeepSeek V3.2 Exp (Reasoning) | deepseek | Sep 2025 | $0.27 / $0.41 | 78.9% | — | #92–334 | ||
| 29 | GPT-5 nano (High) | openai | Aug 2025 | $0.05 / $0.40 | 78.9% | — | #132–399 | ||
| 30 | Qwen3 235B A22B 2507 (Reasoning) | alibaba | Jul 2025 | $0.09 / $0.55 | 78.8% | — | — | ||
| 31 | DeepSeek V3.1 (Reasoning) | deepseek | Aug 2025 | — | 78.4% | — | #101–158 | ||
| 32 | Qwen3 Next 80B A3B (Reasoning) | alibaba | Sep 2025 | $0.15 / $1.20 | 78.4% | — | — | ||
| 33 | Gemini 2.5 Pro Preview (Mar' 25) | — | $1.25 / $10 | 77.8% | — | — | |||
| 34 | gpt-oss-20b (High) | openai | Aug 2025 | $0.02 / $0.09 | 77.7% | — | #156–428 | ||
| 35 | INTELLECT-3 (Based on GLM-4.5-Air) | prime-intellect | Oct 2026 | — | 77.7% | — | #150–397 |
Showing LiveCodeBench (Artificial Analysis) exactly as the source published it — its own score and confidence interval, no blending. Select a second axis to build a weighted composite.