Grok 4.3 (Medium)
83.3%
no interval published
aiqbench · LLM benchmarks
Benchmarks
- Sources
- 8
- Entries tracked
- 22,310
- Last sync
- 31 min31 minutes ago
All sources syncing normally
- Arena · Text· 1 hour ago
- Arena · WebDev· 1 hour ago
- Arena · Vision· 1 hour ago
- Arena · Agent· 1 hour ago
- GPQA Diamond· 31 minutes ago
- SWE-bench· 31 minutes ago
- Terminal-Bench· 31 minutes ago
- ARC-AGI-2· 31 minutes ago
Filter by org:
Released:
Grok 4.20 0309 (Reasoning)
82.9%
no interval published
MiniMax-M3
82.9%
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 | Grok 4.3 (Medium) | xai | Oct 2026 | $1.25 / $2.50 | 83.3% | — | #50–256 | ||
| 2 | Grok 4.20 0309 (Reasoning) | xai | — | — | 82.9% | — | — | ||
| 3 | MiniMax-M3 | minimax | Jun 2026 | $0.30 / $1.20 | 82.9% | — | #50–264 | ||
| 4 | Nemotron 3 Ultra 550B A55B (Reasoning) | nvidia | Jun 2026 | $0.60 / $2.40 | 81.4% | — | — | ||
| 5 | Grok 4.20 0309 v2 (Reasoning) | xai | — | — | 81.2% | — | — | ||
| 6 | Qwen3.7 Max | alibaba | May 2026 | $1.48 / $4.42 | 80.5% | — | #41–128 | ||
| 7 | Nemotron Cascade 2 30B A3B | nvidia | — | — | 80.4% | — | — | ||
| 8 | MiMo-V2.5-Pro (Reasoning) | xiaomi | Apr 2026 | $0.43 / $0.87 | 79.9% | — | #40–129 | ||
| 9 | Nova 2.0 Pro Preview (Low) | aws | — | — | 79.6% | — | — | ||
| 10 | DeepSeek V4 Flash 0420 (Max) | deepseek | — | — | 79.2% | — | — | ||
| 11 | Qwen3.5 397B A17B (Reasoning) | alibaba | Feb 2026 | $0.50 / $3.60 | 78.8% | — | #63–174 | ||
| 12 | Gemini 3 Flash Preview (Reasoning) | — | $0.50 / $3 | 78.0% | — | #27–99 | |||
| 13 | Qwen3.7 Plus | alibaba | Sep 2026 | $0.32 / $1.28 | 78.0% | — | #51–124 | ||
| 14 | GPT-5.2 Codex (Xhigh) | openai | Oct 2026 | $1.75 / $14 | 77.6% | — | #37–370 | ||
| 15 | Gemini 3.1 Flash-Lite | — | $0.25 / $1.50 | 77.2% | — | #170–210 | |||
| 16 | Gemini 3.1 Pro Preview | Sep 2026 | $2 / $12 | 77.1% | — | #9–36 | |||
| 17 | Qwen3.6 Max Preview | alibaba | Oct 2026 | — | 76.6% | — | #34–53 | ||
| 18 | DeepSeek V4 Pro 0424 (Max) | deepseek | — | — | 76.5% | — | — | ||
| 19 | Gemini 3.5 Flash (High) | Sep 2026 | $1.50 / $9 | 76.3% | — | #10–26 | |||
| 20 | GLM-5.1 (Reasoning) | zai | Apr 2026 | $0.97 / $3.04 | 76.3% | — | #44–75 | ||
| 21 | Kimi K2.6 (Reasoning) | kimi | Apr 2026 | $0.65 / $3.41 | 76.0% | — | #29–78 | ||
| 22 | GPT-5.4 nano (Xhigh) | openai | Oct 2026 | $0.20 / $1.25 | 75.9% | — | #95–222 | ||
| 23 | Muse Spark | meta | Sep 2026 | — | 75.9% | — | #16–40 | ||
| 24 | GPT-5.5 (Xhigh) | openai | Sep 2026 | $5 / $30 | 75.9% | — | #9–34 | ||
| 25 | MiniMax-M2.7 | minimax | Apr 2026 | $0.30 / $1.20 | 75.7% | — | #67–241 | ||
| 26 | Qwen3.5 122B A10B (Reasoning) | alibaba | Feb 2026 | $0.26 / $2.08 | 75.7% | — | #105–367 | ||
| 27 | Gemma 4 31B (Reasoning) | Mar 2026 | — | 75.6% | — | #63–214 | |||
| 28 | Qwen3.5 27B (Reasoning) | alibaba | Feb 2026 | $0.26 / $2.60 | 75.6% | — | #109–442 | ||
| 29 | GPT-5 mini (High) | openai | Aug 2025 | $0.25 / $2 | 75.4% | — | #126–343 | ||
| 30 | GPT-5.2 (Xhigh) | openai | Dec 2025 | $1.75 / $14 | 75.4% | — | #34–92 | ||
| 31 | GPT-5.3 Codex (Xhigh) | openai | Oct 2026 | $1.75 / $14 | 75.4% | — | #28–236 | ||
| 32 | Qwen3.6 Plus | alibaba | Oct 2026 | $0.33 / $1.95 | 75.2% | — | #47–265 | ||
| 33 | GPT-5 Codex (High) | openai | — | — | 74.1% | — | #17–142 | ||
| 34 | Command A+ | cohere | Mar 2025 | $2.50 / $10 | 73.9% | — | — | ||
| 35 | GPT-5.4 (Xhigh) | openai | Sep 2026 | $2.50 / $15 | 73.9% | — | #12–29 |
Showing IFBench (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.