OTIS Mock AIME 2024-2025 (Epoch AI)
153 models with a score. Leader: Claude Fable 5.1 with 100 %.
| Benchmark profile | |
|---|---|
| Task | allgemein - Wettbewerbsmathematik |
| Metric | Anteil geloester Aufgaben im AIME-Format (ganzzahlige Antwort), bester Wert ueber die Bewerter |
| Direction | ↑ higher is better |
| Limitation | 🔴 Nicht die offizielle AIME - ein Aufgabensatz im AIME-Format; mit "AIME 2025"-Werten aus Modellkarten nicht vergleichbar. Artificial Analysis misst AIME 2025 nicht mehr, daher Epoch. Reasoning-Stufe entscheidet fast alles (Qwen3-14B 25,8 % ohne, 66,4 % mit). Mathematik hat mit der Anreicherung am wenigsten zu tun - Glied weit hinten in der Kette. |
| As of | 14 Sept 2026 |
| Source | epoch.ai |
| Licence | CC BY 4.0 — Epoch AI |
Ranking (153)
No entry matches the filter.
| Model | Rank | Score | Developer | EU processing: InputEU in | EU processing: OutputEU out | all providers: Inputall in | all providers: Outputall out | Open weights | GPU memory (4-bit, derived)GPU memory |
|---|---|---|---|---|---|---|---|---|---|
| Claude Fable 5.1 | 1 | 100 % | Anthropic | €9.90 | €49.50 | €4.48 | €22.39 | – no | – |
| Claude Opus 5.5 | 1 | 100 % | Anthropic | €3.92 | €19.58 | €1.79 | €8.96 | – no | – |
| Fable 5 | 1 | 100 % | Anthropic | – | – | €4.48 | €22.39 | – no | – |
| Gemini 4 Argon | 1 | 100 % | €2.02 | €10.10 | €0.90 | €4.48 | – no | – | |
| GPT-5.6 sol | 1 | 100 % | OpenAI | €3.94 | €19.70 | €1.79 | €8.96 | – no | – |
| GPT-6 astra | 1 | 100 % | OpenAI | €9.68 | €48.40 | €4.48 | €22.39 | – no | – |
| GPT-6 sol | 1 | 100 % | OpenAI | €2.15 | €10.75 | €0.90 | €4.48 | – no | – |
| GPT-6.1 Sol | 1 | 100 % | OpenAI | €2.14 | €10.68 | €0.90 | €4.48 | – no | – |
| GPT-6.1 Terra | 1 | 100 % | OpenAI | €1.06 | €5.28 | €0.45 | €2.24 | – | – |
| Kimi K3.1 Pro | 1 | 100 % | Moonshot AI | €1.79 | €8.96 | €1.79 | €8.96 | – no | – |
| Sonnet 5.5 | 1 | 100 % | Anthropic | €2.02 | €10.10 | €0.90 | €4.48 | – no | – |
| GPT-5.6 terra | 12 | 99.7 % | OpenAI | €1.97 | €11.82 | €0.90 | €5.37 | – no | – |
| DeepSeek V4.1 Flash 1017 | 13 | 99.4 % | DeepSeek | €0.18 | €0.54 | €0.18 | €0.54 | – no | – |
| Mistral Large 4 | 13 | 99.4 % | Mistral AI | €0.50 | €1.75 | €0.50 | €1.75 | ✓ yes | from 582 GB |
| Muse Wonder | 13 | 99.4 % | – | – | – | €3.58 | €17.91 | – no | – |
| Qwen3.8-Max | 13 | 99.4 % | Alibaba Cloud | €2.24 | €5.39 | €1.48 | €4.43 | ✓ yes | from 1,350 GB |
| Grok 4.6 | 17 | 99.2 % | xAI | – | – | €1.79 | €5.37 | – no | – |
| Gemini 3.8 Flash | 18 | 98.9 % | €0.74 | €3.68 | €0.34 | €1.68 | – no | – | |
| GPT-6 luna | 18 | 98.9 % | OpenAI | €0.11 | €0.54 | €0.045 | €0.22 | – no | – |
| Haiku 5.5 | 18 | 98.9 % | Anthropic | €0.10 | €0.51 | €0.045 | €0.22 | – no | – |
| Opus 5 | 18 | 98.9 % | Anthropic | €4.94 | €24.68 | €2.24 | €11.20 | – no | – |
| DeepSeek V4 Pro 0813 | 22 | 98.6 % | DeepSeek | €1.79 | €3.58 | €1.16 | €2.33 | ✓ yes | from 912 GB |
| GPT-5.6 luna | 23 | 98.3 % | OpenAI | €0.20 | €1.18 | €0.09 | €0.54 | – no | – |
| Opus 4.8 | 23 | 98.3 % | Anthropic | €4.88 | €24.40 | €2.24 | €11.20 | – no | – |
| Grok 4.7 | 25 | 98.1 % | xAI | – | – | €1.79 | €5.37 | – no | – |
| Muse Spark Open | 25 | 98.1 % | – | – | – | €1.12 | €3.81 | – | – |
| Grok 4.5 | 27 | 97.8 % | xAI | – | – | €1.79 | €5.37 | – no | – |
| Opus 4.7 | 27 | 97.8 % | Anthropic | €4.88 | €24.40 | €2.24 | €11.20 | – no | – |
| Gemini 3.7 Flash | 29 | 97.2 % | €0.67 | €3.37 | €0.34 | €1.68 | – no | – | |
| Kimi K3 | 29 | 97.2 % | Moonshot AI | €2.55 | €12.76 | €1.66 | €8.51 | ✓ yes | from 1,533 GB |
| GPT-5.2 | 31 | 96.1 % | OpenAI | €1.72 | €13.79 | €0.78 | €6.27 | – no | – |
| Kimi K2.6 | 31 | 96.1 % | Moonshot AI | €0.43 | €2.67 | €0.35 | €1.61 | ✓ yes | from 569 GB |
| Gemini 3 Flash Preview | 33 | 95.6 % | – | – | €0.22 | €1.34 | – no | – | |
| Gemini 3.1 Pro (Vorschau) | 33 | 95.6 % | – | – | €0.90 | €5.37 | – no | – | |
| Gemini 3.5 Flash | 33 | 95.6 % | €1.48 | €8.89 | €0.67 | €4.03 | – no | – | |
| Kimi K2.7 Code | 33 | 95.6 % | Moonshot AI | €0.59 | €2.96 | €0.59 | €2.96 | ✓ yes | from 554 GB |
| Qwen 3.7 Max | 33 | 95.6 % | Alibaba Cloud | – | – | €1.12 | €3.36 | – no | – |
| DeepSeek V4 Pro | 38 | 95.56 % | DeepSeek | €0.90 | €1.79 | €0.90 | €1.79 | ✓ yes | from 884 GB |
| Claude Sonnet 5 | 39 | 94.7 % | Anthropic | €1.98 | €9.87 | €0.90 | €4.48 | – no | – |
| DeepSeek V4 Flash 0731 | 40 | 94.4 % | DeepSeek | €0.10 | €0.25 | €0.054 | €0.16 | ✓ yes | from 172 GB |
| Opus 4.6 | 40 | 94.4 % | Anthropic | €4.77 | €23.84 | €2.24 | €11.20 | – no | – |
| Gemini 3.6 Flash | 42 | 94.2 % | €0.67 | €3.37 | €0.34 | €1.68 | – no | – | |
| GLM 5.3 Flash | 43 | 93.9 % | Z.ai | €0.09 | €0.31 | €0.09 | €0.31 | ✓ yes | from 180 GB |
| Qwen3.7-Plus | 44 | 93.33 % | Alibaba Cloud | – | – | €0.29 | €1.15 | – no | – |
| GLM 5.1 | 45 | 93.3 % | Z.ai | €1.24 | €3.90 | €0.81 | €2.60 | ✓ yes | from 419 GB |
| Grok 4.3 | 45 | 93.3 % | xAI | – | – | €1.12 | €2.24 | – no | – |
| Qwen 3.6 Plus | 45 | 93.3 % | Alibaba Cloud | – | – | €0.45 | €2.69 | – no | – |
| Grok 4.20 | 48 | 92.2 % | xAI | – | – | €1.27 | €2.53 | – no | – |
| Grok 4.20 Reasoning | 48 | 92.2 % | xAI | – | – | €1.12 | €2.24 | – no | – |
| grok-4.20-0309-reasoning | 48 | 92.2 % | xAI | – | – | €1.12 | €2.24 | – no | – |
| Kimi K2.5 (Retiring) | 48 | 92.2 % | Moonshot AI | €0.58 | €3.22 | €0.27 | €1.34 | ✓ yes | from 554 GB |
| gpt-5 | 52 | 91.4 % | OpenAI | €0.62 | €4.93 | €0.56 | €4.48 | – no | – |
| GPT-5 2025-08-07 | 52 | 91.4 % | OpenAI | – | – | €0.56 | €4.48 | – no | – |
| Qwen3.6-27B | 54 | 91.11 % | Alibaba Cloud | €0.40 | €2.70 | €0.22 | €1.79 | ✓ yes | from 20 GB |
| glm-5.3 | 55 | 91.1 % | Z.ai | €0.45 | €1.79 | €0.18 | €0.57 | ✓ yes | from 419 GB |
| gpt-oss-120b | 56 | 88.9 % | OpenAI | €0.026 | €0.12 | €0.026 | €0.12 | ✓ yes | from 69 GB |
| Muse Spark | 56 | 88.9 % | – | – | – | €0.09 | €0.18 | – | – |
| Qwen3.5-397B-A17B | 58 | 88.89 % | Alibaba Cloud | €0.60 | €3.58 | €0.40 | €2.69 | ✓ yes | from 226 GB |
| gpt-5.1 | 59 | 88.6 % | OpenAI | €1.23 | €9.84 | €0.56 | €4.48 | – no | – |
| GPT-5.4 mini | 60 | 87.22 % | OpenAI | €0.74 | €4.43 | €0.34 | €2.02 | – no | – |
| GPT-5 mini | 61 | 86.7 % | OpenAI | €0.25 | €1.97 | €0.11 | €0.90 | – no | – |
| NVIDIA Nemotron 3 Ultra | 61 | 86.7 % | NVIDIA | – | – | €0.45 | €1.97 | ✓ yes | from 307 GB |
| Qwen 3 235B A22B Thinking 2507 | 61 | 86.7 % | Alibaba Cloud | – | – | €0.40 | €3.13 | ✓ yes | from 134 GB |
| Qwen3.6-35B-A3B | 64 | 86.67 % | Alibaba Cloud | €0.13 | €0.45 | €0.13 | €0.45 | ✓ yes | from 24 GB |
| glm-5.2 | 65 | 86.4 % | Z.ai | €0.81 | €2.91 | €0.15 | €0.48 | ✓ yes | from 419 GB |
| Opus 4.5 | 66 | 86.1 % | Anthropic | €4.77 | €23.85 | €2.24 | €11.20 | – no | – |
| Gemini 2.5 Pro | 67 | 84.7 % | €1.34 | €8.94 | €0.56 | €4.48 | – no | – | |
| GPT-5.4 | 68 | 84.44 % | OpenAI | €2.60 | €13.87 | €1.12 | €6.72 | – no | – |
| Qwen3.5-Flash | 68 | 84.44 % | Alibaba Cloud | – | – | – | – | – no | – |
| GPT-5.5 | 70 | 84.4 % | OpenAI | €4.93 | €29.56 | €2.24 | €13.43 | – no | – |
| o3 | 70 | 84.4 % | OpenAI | – | – | €0.90 | €3.58 | – no | – |
| o3 2025-04-16 | 70 | 84.4 % | OpenAI | €0.99 | €3.94 | €0.90 | €3.58 | – no | – |
| GLM 4.7 | 73 | 83.3 % | Z.ai | – | – | €0.27 | €0.99 | ✓ yes | from 201 GB |
| Claude Sonnet 4.6 | 74 | 82.2 % | Anthropic | €2.87 | €14.31 | €1.34 | €6.72 | – no | – |
| Gemma 4 26B A4B | 74 | 82.2 % | €0.11 | €0.27 | €0.063 | €0.30 | – | – | |
| o4-mini 2025-04-16 | 76 | 81.7 % | OpenAI | €0.54 | €2.17 | €0.49 | €1.97 | – no | – |
| GPT-5 nano | 77 | 81.1 % | OpenAI | €0.049 | €0.39 | €0.022 | €0.18 | – no | – |
| GLM-5 | 78 | 80 % | Z.ai | €1.15 | €3.68 | €0.45 | €1.43 | – | – |
| Sonnet 4.5 | 79 | 77.8 % | Anthropic | €2.68 | €13.42 | €1.34 | €6.72 | – no | – |
| o3 mini 2025-01-31 | 80 | 76.9 % | OpenAI | €0.54 | €2.17 | €0.49 | €1.97 | – no | – |
| Qwen3-Max | 81 | 73.33 % | Alibaba Cloud | – | – | – | – | – no | – |
| Gemma 4 31B | 82 | 73.3 % | €0.09 | €0.27 | €0.09 | €0.27 | ✓ yes | from 22 GB | |
| o1 2024-12-17 | 82 | 73.3 % | OpenAI | €14.78 | €59.11 | €13.43 | €53.74 | – no | – |
| Claude Sonnet 4 (retired, except on Claude Models on Google Cloud (Google managed) and Bedrock) | 84 | 71.1 % | Anthropic | – | – | €1.34 | €6.72 | – no | – |
| Gemini 3.5 Flash-Lite | 84 | 71.1 % | €0.30 | €2.47 | €0.13 | €1.12 | – no | – | |
| MiniMax M3 | 84 | 71.1 % | MiniMax | €0.27 | €1.08 | €0.27 | €1.07 | ✓ yes | from 239 GB |
| Qwen3.5-35B-A3B | 87 | 70 % | Alibaba Cloud | – | – | €0.13 | €0.90 | ✓ yes | from 24 GB |
| Claude Opus 4.1 (retired, except on Claude Models on Google Cloud (Google managed) and Bedrock) | 88 | 68.9 % | Anthropic | – | – | €6.72 | €33.59 | – no | – |
| GPT-5.4 nano | 89 | 68.89 % | OpenAI | – | – | €0.09 | €0.56 | – no | – |
| Seed-OSS-36B-Instruct | 90 | 67.5 % | ByteDance | – | – | – | – | ✓ yes | from 24 GB |
| Qwen3-32B | 91 | 66.94 % | qwen-alibaba | €0.28 | €0.28 | €0.072 | €0.25 | ✓ yes | from 23 GB |
| Claude Haiku 4.5 | 92 | 66.67 % | Anthropic | €0.89 | €4.47 | €0.45 | €2.24 | – no | – |
| DeepSeek-R1 (0528) | 93 | 66.4 % | DeepSeek | – | – | €0.45 | €1.93 | ✓ yes | from 381 GB |
| Qwen3-14B | 94 | 66.39 % | Alibaba Cloud | €0.18 | €0.90 | €0.11 | €0.21 | ✓ yes | from 13 GB |
| Claude Opus 4 (retired, except on Claude Models on Google Cloud (Google managed)) | 95 | 64.4 % | Anthropic | – | – | €6.72 | €33.59 | – no | – |
| Qwen3-30B-A3B | 96 | 62.8 % | Alibaba Cloud | – | – | €0.046 | €0.30 | ✓ yes | from 21 GB |
| Qwen3 30B A3B Instruct 2507 | 97 | 62.2 % | Alibaba Cloud | €0.089 | €0.27 | €0.089 | €0.27 | ✓ yes | from 21 GB |
| Qwen3.5-9B | 98 | 61.7 % | Alibaba Cloud | €0.09 | €0.13 | €0.09 | €0.13 | ✓ yes | from 10 GB |
| GLM 4.7 Flash | 99 | 58.3 % | Z.ai | €0.072 | €0.43 | €0.031 | €0.18 | ✓ yes | from 21 GB |
| Claude 3.7 Sonnet | 100 | 57.8 % | Anthropic | – | – | €1.34 | €6.72 | – | – |
| Qwen3 8B | 101 | 56.1 % | Alibaba Cloud | – | – | – | – | ✓ yes | from 9 GB |
| o1-mini 2024-09-12 | 102 | 46.9 % | OpenAI | €1.08 | €4.33 | €0.99 | €3.94 | – no | – |
| gpt-4.1-mini | 103 | 44.7 % | OpenAI | €0.39 | €1.53 | €0.18 | €0.72 | – no | – |
| GPT-4.1-mini-2025-04-14 | 103 | 44.7 % | OpenAI | €0.20 | €0.79 | €0.18 | €0.72 | – no | – |
| gpt-oss-20b | 105 | 40.3 % | OpenAI | €0.024 | €0.11 | €0.024 | €0.11 | ✓ yes | from 16 GB |
| GPT-4.1 | 106 | 38.3 % | OpenAI | €1.97 | €7.87 | €0.90 | €3.58 | – no | – |
| GPT-4.1-2025-04-14 | 106 | 38.3 % | OpenAI | €0.99 | €3.94 | €0.90 | €3.58 | – no | – |
| Gemini 3.1 Flash-Lite | 108 | 37.8 % | €0.24 | €1.46 | €0.11 | €0.67 | – no | – | |
| GPT-4.5-Preview-2025-02-27 | 108 | 37.8 % | OpenAI | – | – | €67.17 | €134.35 | – no | – |
| Mistral Medium 3 | 110 | 32.2 % | Mistral AI | – | – | €0.36 | €1.79 | – no | – |
| Gemini 2.0 Flash | 111 | 31.1 % | – | – | €0.067 | €0.27 | – no | – | |
| o1 preview 2024-09-12 | 111 | 31.1 % | OpenAI | €14.78 | €59.11 | €13.43 | €53.74 | – no | – |
| Mistral Small 3.2 24B | 113 | 30.3 % | Mistral AI | €0.061 | €0.16 | €0.061 | €0.16 | ✓ yes | from 18 GB |
| gpt-4.1-nano | 114 | 28.9 % | OpenAI | €0.10 | €0.39 | €0.10 | €0.39 | – no | – |
| GPT-4.1-nano-2025-04-14 | 114 | 28.9 % | OpenAI | €0.049 | €0.20 | €0.045 | €0.18 | – no | – |
| Magistral Small 1.2 | 116 | 28.1 % | Mistral AI | – | – | €0.22 | €0.67 | ✓ yes | from 18 GB |
| Gemma 3 27B | 117 | 22.5 % | €0.089 | €0.27 | €0.072 | €0.14 | ✓ yes | from 20 GB | |
| Llama 4 Maverick | 118 | 20.6 % | Meta | – | – | €0.16 | €0.52 | ✓ yes | from 225 GB |
| Gemma 3 12B | 119 | 16.7 % | – | – | €0.045 | €0.13 | ✓ yes | from 11 GB | |
| DeepSeek-V3 | 120 | 15.8 % | DeepSeek | – | – | €0.29 | €0.80 | ✓ yes | from 381 GB |
| Phi-4 | 121 | 13.8 % | Microsoft | – | – | €0.063 | €0.13 | ✓ yes | from 13 GB |
| Claude 3.5 Sonnet v2 | 122 | 8.5 % | Anthropic | – | – | €1.34 | €6.72 | – | – |
| Qwen2.5-72B-Instruct | 123 | 8.1 % | Alibaba Cloud | – | – | €0.32 | €0.36 | ✓ yes | from 44 GB |
| Llama 4 Scout 17B-16E | 124 | 7.8 % | Meta | – | – | €0.09 | €0.27 | ✓ yes | from 64 GB |
| Mistral Large 2.1 | 124 | 7.8 % | Mistral AI | – | – | – | – | ✓ yes | from 72 GB |
| Gemma 3 4B | 126 | 7.5 % | – | – | €0.018 | €0.036 | ✓ yes | from 7 GB | |
| GPT-4o mini | 127 | 6.9 % | OpenAI | €0.14 | €0.57 | €0.067 | €0.27 | – no | – |
| GPT-4o-mini-0718 | 127 | 6.9 % | OpenAI | €0.15 | €0.59 | €0.067 | €0.27 | – no | – |
| Mistral Small 3 24B | 129 | 6.7 % | Mistral AI | – | – | €0.045 | €0.072 | ✓ yes | from 17 GB |
| Claude 3.5 Sonnet | 130 | 6.5 % | Anthropic | – | – | €1.34 | €6.72 | – | – |
| GPT-4o | 131 | 6.4 % | OpenAI | €2.39 | €9.55 | €1.12 | €4.48 | – no | – |
| GPT-4o-2024-08-06 | 131 | 6.4 % | OpenAI | €1.23 | €4.93 | €1.12 | €4.48 | – no | – |
| GPT-4o-2024-0513 | 133 | 6.2 % | OpenAI | €4.93 | €14.78 | €2.24 | €6.72 | – no | – |
| GPT-4o-2024-1120 | 133 | 6.2 % | OpenAI | €2.46 | €9.85 | €1.12 | €4.48 | – no | – |
| Llama 3.3 70B | 135 | 5.1 % | Meta | €0.45 | €0.65 | €0.09 | €0.29 | ✓ yes | from 43 GB |
| Claude 3 Opus | 136 | 4.7 % | Anthropic | – | – | €6.72 | €33.59 | – | – |
| Claude 3.5 Haiku | 137 | 4.3 % | Anthropic | – | – | €0.36 | €1.79 | – no | – |
| Llama 3 70B | 137 | 4.3 % | Meta | – | – | €2.37 | €3.13 | ✓ yes | from 43 GB |
| Mistral Small 3.1 24B | 139 | 3.9 % | Mistral AI | €0.099 | €0.30 | €0.09 | €0.27 | ✓ yes | from 18 GB |
| Llama 3.1 70B | 140 | 3.6 % | Meta | €0.31 | €1.25 | €0.31 | €1.25 | ✓ yes | from 43 GB |
| Llama 3.2 90B | 141 | 2.6 % | Meta | – | – | €0.64 | €0.64 | ✓ yes | from 53 GB |
| Claude 3 Sonnet | 142 | 2.5 % | Anthropic | – | – | €1.34 | €6.72 | – no | – |
| Qwen 2.5 7B | 142 | 2.5 % | Alibaba Cloud | €0.033 | €0.082 | €0.033 | €0.082 | ✓ yes | from 9 GB |
| GPT-3.5-Turbo-0125 | 144 | 2.2 % | OpenAI | – | – | €0.54 | €1.63 | – no | – |
| Llama 3 8B | 145 | 1.9 % | Meta | – | – | €0.11 | €0.24 | ✓ yes | from 9 GB |
| mistral-large-2402 | 145 | 1.9 % | Mistral AI | €3.85 | €11.63 | €3.85 | €11.63 | – no | – |
| Claude 3 Haiku | 147 | 1.8 % | Anthropic | – | – | €0.11 | €0.56 | – no | – |
| Llama 3.1 8B Instruct | 148 | 1.7 % | Meta | €0.016 | €0.041 | €0.018 | €0.036 | ✓ yes | from 9 GB |
| Gemini 1.0 Pro | 149 | 1.1 % | – | – | – | – | – no | – | |
| Gemma 2 9B | 150 | 0.6 % | – | – | – | – | ✓ yes | from 10 GB | |
| Llama 3.2 1B | 150 | 0.6 % | Meta | – | – | €0.024 | €0.18 | ✓ yes | from 5 GB |
| Mistral 7B Instruct | 152 | 0.3 % | Mistral AI | €0.12 | €0.12 | €0.12 | €0.12 | ✓ yes | from 8 GB |
| Meta Llama 2 Chat 70B | 153 | 0 % | Meta | – | – | €1.75 | €2.29 | – | – |
Equal scores share a rank. When filtering, the rank stays the position in the whole list. GPU memory “from …” is a lower bound (parameters × 0.55 GB + 4 GB). Prices: € per 1M tokens. Source: providers' pricing pages, read and checked by searchit. As of 7 Nov 2026.
Price and performance
Scores: OTIS Mock AIME 2024-2025 (Epoch AI), CC BY 4.0 — Epoch AI. Taken unchanged from the source.