Filter by Provider:
Last updated on: 6th Oct 2025
Use horizontal scroll, buttons, or Ctrl+Arrow keys
Scroll Progress:
0%
Swipe horizontally to scroll
Model | Org. | Safety Rank | Safe Responses | Unsafe Responses | Jailbreaking Resistance | Code LMArena (old) | Math LiveBench | GPQA | Code LiveBench | Code RankedAGI | Multimodal Support | Available on  | Available on  | Available on  | Size Parameters | Released | Knowledge Cutoff | Input Cost/M | Output Cost/M | Context Length | Latency TTFT |
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
 Kimi K2 Instruct 0905 | Moonshot AI | #15 | 81% | 19% (58 / 300) | 42% (42 / 100) | - | - | 0.76/1 | - | - | Yes | No | No | No | 32B (1T total) | 05-Sep-24 | 2024-09 | $0.60 | $2.50 | 256K tokens | - |
 Grok 4 | xAI | #22 | 61% | 39% (116 / 300) | 10% (10 / 100) | 1420 | 88.84% | 88.10% | 71.34% | - | Yes | No | No | No | - | 09-Jul-25 | 2025-07 | $3.00 | $15.00 | 256K tokens | ~11s |
 GPT-4.1 | OpenAI | #9 | 93% | 7% (22 / 300) | 83% (83 / 100) | 1385 | 72.00% | 66.30% | 54.60% | 50.3% | Yes | No | Yes | Yes | - | 14-Apr-25 | 2024-06-01 | $2.00 | $8.00 | 1M tokens | ~0.4s |
GPT-4.1 Mini | OpenAI | #7 | 96% | 4% (12 / 300) | 89% (89 / 100) | 1365 | 45.2% | 65.0% | 42.8% | 35.5% | Yes | No | Yes | Yes | - | 14-Apr-25 | 2025-01 | $0.40 | $1.60 | 1M tokens | ~0.43s |
GPT-4.5 | OpenAI | #3 | 100% | 0% (1 / 237) | 97% (36 / 37) | 1362 | 69.30% | 69.50% | 76.10% | 58.6% | Yes | No | No | No | - | 27-Feb-25 | 2023-10-01 | $75.00 | $150.00 | 128K tokens | ~0.5s |
GPT-5 | OpenAI | #11 | 91% | 9% (26 / 300) | 75% (75 / 100) | 1450 | 92.77% | 86.00% | 75.31% | 39.8% | Yes | No | Yes | No | - | 07-Aug-25 | 2024-10-01 | $1.25 | $10.00 | 400K tokens | Medium |
 Claude Opus 4.1 | Anthropic | #5 | 99% | 1% (4 / 300) | 97% (97 / 100) | - | 90.0% | 83.3% | 74.5% | 74.5% | Yes | Yes | No | Yes | - | 05-Aug-25 | 2025-03-01 | $15.00 | $75.00 | 200K tokens | Moderately Fast |
GPT-4o | OpenAI | #10 | 93% | 7% (20 / 300) | 82% (82 / 100) | 1385 | 41.48% | 46.00% | 77.50% | 61.4% | Yes | No | Yes | No | - | 20-Nov-24 | 2023-10-01 | $2.50 | $10.00 | 128K tokens | ~0.6s |
Claude 3.7 Sonnet | Anthropic | #2 | 100% | 0% (1 / 300) | 99% (99 / 100) | 1326 | 63.30% | 84.80% | 73.2% | 60.4% | Yes | Yes | No | Yes | 70B | 24-Feb-25 | 2024-10-01 | $3.00 | $15.00 | 200K tokens | - |
 DeepSeek R1 | DeepSeek | #12 | 89% | 11% (26 / 237) | 32% (12 / 37) | 1380 | 79.50% | 74.24% | 48.50% | - | No | No | No | No | 671B | 20-Jan-25 | 2024-07-01 | $0.55 | $2.19 | 128K tokens | - |
 Gemini 2.5 Pro Preview | #19 | 66% | 34% (102 / 300) | 26% (26 / 100) | 1395 | 84.19% | 86.40% | 73.90% | - | Yes | Yes | No | No | - | 05-Jun-25 | 2025-01-31 | $1.25 | $10.00 | 1M tokens | - | |
Gemini 2.5 Flash Preview 05-20 | #21 | 63% | 37% (111 / 300) | 12% (12 / 100) | 1350 | 84.10% | 82.80% | 63.53% | - | Yes | Yes | No | No | - | 17-Apr-25 | 2025-01-31 | $0.15 | $0.60 | 1M tokens | - | |
Gemini 2.0 Flash | #20 | 66% | 34% (102 / 300) | 10% (10 / 100) | 1310 | 83.33% | 62.10% | 70.70% | - | Yes | Yes | No | No | - | 05-Feb-25 | 2024-08-01 | $0.10 | $0.40 | 1M tokens | - | |
Gemma 2 9B | #14 | 84% | 16% (37 / 237) | 5% (2 / 37) | 1180 | 52.27% | - | 48.94% | - | No | - | - | - | 9B | 27-Jun-24 | 2024-04-01 | - | - | 8K tokens | - | |
Grok-3 | xAI | #23 | 22% | 78% (235 / 300) | 3% (3 / 100) | 1320 | 62.75% | 84.60% | 73.58% | - | Yes | - | - | - | 300B | 01-May-24 | 2024-11 | $3.00 | $15.00 | 128K tokens | - |
 Llama 4 Maverick 128e Instruct | Meta | #17 | 79% | 21% (50 / 237) | 3% (1 / 37) | 1290 | 60.58% | - | 54.19% | - | No | - | - | - | 17B | 05-Apr-25 | 2024-08-01 | $0.20 | $0.60 | 128K tokens | - |
Llama 3.1 Instant | Meta | #16 | 79% | 21% (49 / 237) | 3% (1 / 37) | 1200 | 51.88% | - | 57.26% | - | No | - | - | - | 8B | 23-Jul-24 | 2023-12-01 | - | - | 128K tokens | - |
Llama 4 Scout 16e Instruct | Meta | #18 | 78% | 22% (52 / 237) | 3% (1 / 37) | 1250 | 48.14% | - | 42.16% | - | No | - | - | - | 17B | 05-Apr-25 | 2024-08-01 | - | - | 128K tokens | - |
 QWen-qwq-32b | Alibaba Cloud | #13 | 87% | 13% (31 / 237) | 32% (12 / 37) | 1340 | 81.14% | - | 67.18% | - | No | - | - | - | 32B | 12-Oct-24 | 2024-09-01 | - | - | 128K tokens | - |
GPT-OSS-20B | OpenAI | #8 | 96% | 4% (11 / 300) | 89% (89 / 100) | - | 69.54% | 71.5% | - | 24.8% | No | No | Yes | Yes | 20B | 05-Aug-25 | - | - | - | 128K tokens | - |
GPT-OSS-120B | OpenAI | #6 | 97% | 3% (8 / 300) | 92% (92 / 100) | - | 69.54% | 80.1% | 58.80% | 35.5% | No | No | Yes | Yes | 120B | 05-Aug-25 | - | - | - | 128K tokens | - |
Claude Sonnet 4.5 | Anthropic | #1 | 100% | 0% (1 / 300) | 100% (100 / 100) | 1420 | 75.0% | 85.0% | 77.2% | 82.0% | Yes | - | - | - | - | 29-Sep-25 | 2025-04-01 | $3.00 | $15.00 | 200K tokens | ~0.5s |
Claude 4 Sonnet | Anthropic | #4 | 99% | 1% (4 / 300) | 97% (97 / 100) | 1410 | 70.5% | 75.40% | 64.8% | 78.3% | Yes | Yes | No | Yes | - | 22-May-25 | 2024-04-01 | $3.00 | $15.00 | 200K tokens | ~0.5-1s |
📊 Data Source
All comparative insights are based on a combination of rigorous red teaming and jailbreaking testing performed by Holistic AI, as well as publicly available benchmark data. External benchmarks include CodeLMArena, MathLiveBench, CodeLiveBench, and GPQA. These were sourced from official model provider websites, public leaderboards, benchmark sites, and other accessible resources to ensure transparency, accuracy, and reliability.