| 1≈ |
GPT-6.1 Sol (high reasoning)OpenAI |
0.0%
|
$2 / $10 |
| 1≈ |
GPT-6.1 Sol (extra-high reasoning)OpenAI |
0.0%
|
$2 / $10 |
| 1≈ |
GPT-6 Astra (high reasoning)OpenAI |
0.0%
|
$10 / $50 |
| 1≈ |
GPT-6 Astra (extra-high reasoning)OpenAI |
0.0%
|
$10 / $50 |
| 5 |
Claude Opus 4.7 (low reasoning)Anthropic |
1.0%
|
$5 / $25 |
| 5 |
GPT-5.6 Sol (extra-high reasoning)OpenAI |
1.0%
|
$4 / $20 |
| 5 |
GPT-6.1 Sol (low reasoning)OpenAI |
1.0%
|
$2 / $10 |
| 5 |
GPT-6 Astra (low reasoning)OpenAI |
1.0%
|
$10 / $50 |
| 5 |
GPT-6 Astra (medium reasoning)OpenAI |
1.0%
|
$10 / $50 |
| 10 |
Claude Fable 5 (high reasoning)Anthropic |
2.0%
|
$10 / $50 |
| 10 |
Claude Fable 5 (low reasoning)Anthropic |
2.0%
|
$10 / $50 |
| 10 |
Claude Fable 5 (max reasoning)Anthropic |
2.0%
|
$10 / $50 |
| 10 |
Claude Fable 5 (medium reasoning)Anthropic |
2.0%
|
$10 / $50 |
| 10 |
Claude Fable 5 (extra-high reasoning)Anthropic |
2.0%
|
$10 / $50 |
| 10 |
Claude Opus 4.7 (high reasoning)Anthropic |
2.0%
|
$5 / $25 |
| 10 |
Claude Opus 4.7 (medium reasoning)Anthropic |
2.0%
|
$5 / $25 |
| 10 |
Claude Opus 5.5 (max reasoning)Anthropic |
2.0%
|
$4 / $20 |
| 10 |
Claude Sonnet 4.6 (low reasoning)Anthropic |
2.0%
|
$3 / $15 |
| 10 |
Claude Sonnet 4.6 (max reasoning)Anthropic |
2.0%
|
$3 / $15 |
| 10 |
Claude Sonnet 4.6 (medium reasoning)Anthropic |
2.0%
|
$3 / $15 |
| 10 |
GPT-6.1 Sol (medium reasoning)OpenAI |
2.0%
|
$2 / $10 |
| 22 |
Claude Fable 5.1 (high reasoning)Anthropic |
3.0%
|
$10 / $50 |
| 22 |
Claude Fable 5.1 (medium reasoning)Anthropic |
3.0%
|
$10 / $50 |
| 22 |
Claude Opus 4.1 (no reasoning)Anthropic |
3.0%
|
$15 / $75 |
| 22 |
Claude Opus 4.5 (no reasoning)Anthropic |
3.0%
|
$5 / $25 |
| 22 |
Claude Opus 4.6 (max reasoning)Anthropic |
3.0%
|
$5 / $25 |
| 22 |
Claude Opus 4.7 (max reasoning)Anthropic |
3.0%
|
$5 / $25 |
| 22 |
Claude Sonnet 4.6 (high reasoning)Anthropic |
3.0%
|
$3 / $15 |
| 22 |
Claude Sonnet 5 (high reasoning)Anthropic |
3.0%
|
$2 / $10 |
| 22 |
Claude Sonnet 5 (low reasoning)Anthropic |
3.0%
|
$2 / $10 |
| 22 |
Claude Sonnet 5 (medium reasoning)Anthropic |
3.0%
|
$2 / $10 |
| 32 |
Claude Fable 5.1 (low reasoning)Anthropic |
4.0%
|
$10 / $50 |
| 32 |
Claude Opus 4.5 (reasoning on)Anthropic |
4.0%
|
$5 / $25 |
| 32 |
Claude Opus 4.6 (low reasoning)Anthropic |
4.0%
|
$5 / $25 |
| 32 |
Claude Opus 4.6 (medium reasoning)Anthropic |
4.0%
|
$5 / $25 |
| 32 |
Claude Sonnet 4 (no reasoning)Anthropic |
4.0%
|
$3 / $15 |
| 32 |
GPT-5.6 Sol (high reasoning)OpenAI |
4.0%
|
$4 / $20 |
| 32 |
GPT-6 Sol (high reasoning)OpenAI |
4.0%
|
$2 / $10 |
| 32 |
GPT-6 Sol (medium reasoning)OpenAI |
4.0%
|
$2 / $10 |
| 32 |
GPT-6 Sol (extra-high reasoning)OpenAI |
4.0%
|
$2 / $10 |
| 41 |
Claude Opus 4.6 (high reasoning)Anthropic |
5.0%
|
$5 / $25 |
| 41 |
Claude Opus 5.5 (high reasoning)Anthropic |
5.0%
|
$4 / $20 |
| 41 |
Claude Opus 5.5 (low reasoning)Anthropic |
5.0%
|
$4 / $20 |
| 41 |
Claude Opus 5.5 (medium reasoning)Anthropic |
5.0%
|
$4 / $20 |
| 41 |
Claude Opus 5.5 (extra-high reasoning)Anthropic |
5.0%
|
$4 / $20 |
| 41 |
Claude Sonnet 4.5 (no reasoning)Anthropic |
5.0%
|
$3 / $15 |
| 41 |
Gemma 4 31BGoogle |
5.0%
|
$0.14 / $0.40 |
| 41 |
GPT-6 Sol (low reasoning)OpenAI |
5.0%
|
$2 / $10 |
| 49 |
Claude Haiku 4.5 (no reasoning)Anthropic |
6.0%
|
$1 / $5 |
| 49 |
Claude Opus 4.8 (extra-high reasoning)Anthropic |
6.0%
|
$5 / $25 |
| 49 |
Claude Opus 4 (no reasoning)Anthropic |
6.0%
|
– |
| 49 |
Claude Opus 4 (reasoning on)Anthropic |
6.0%
|
– |
| 49 |
Claude Sonnet 5 (max reasoning)Anthropic |
6.0%
|
$2 / $10 |
| 49 |
Gemma 4 31B (reasoning by prefill)Google |
6.0%
|
$0.14 / $0.40 |
| 49 |
GPT-4.1OpenAI |
6.0%
|
$2 / $8 |
| 56 |
Qwen3-Next-80B-A3B-InstructAlibaba |
7.0%
|
$0.10 / $1.10 |
| 56 |
Claude 3.7 Sonnet (no reasoning)Anthropic |
7.0%
|
– |
| 56 |
Claude Opus 4.8 (low reasoning)Anthropic |
7.0%
|
$5 / $25 |
| 56 |
Claude Sonnet 5 (extra-high reasoning)Anthropic |
7.0%
|
$2 / $10 |
| 56 |
Gemini 3.7 Flash (medium reasoning)Google |
7.0%
|
$1.50 / $7.50 |
| 56 |
GPT-5.6 Sol (medium reasoning)OpenAI |
7.0%
|
$4 / $20 |
| 56 |
Grok 4.1 Fast (reasoning)xAI |
7.0%
|
– |
| 63 |
Qwen3-4B-Instruct-2507Alibaba |
8.0%
|
– |
| 63 |
Qwen3.6-Plus (reasoning on)Alibaba |
8.0%
|
$0.33 / $1.95 |
| 63 |
Claude Sonnet 4.5 (reasoning on)Anthropic |
8.0%
|
$3 / $15 |
| 63 |
Gemini 3.7 Flash (high reasoning)Google |
8.0%
|
$1.50 / $7.50 |
| 63 |
Gemma 3 27BGoogle |
8.0%
|
$0.12 / $0.20 |
| 63 |
Gemma 4 12B (reasoning by prefill)Google |
8.0%
|
– |
| 63 |
Gemma 4 12BGoogle |
8.0%
|
– |
| 63 |
Gemma 4 26B A4B (reasoning by prefill)Google |
8.0%
|
$0.10 / $0.30 |
| 63 |
Gemma 4 26B A4BGoogle |
8.0%
|
$0.10 / $0.30 |
| 63 |
Mistral Small 3Mistral AI |
8.0%
|
$0.05 / $0.08 |
| 63 |
GPT-5.3 ChatOpenAI |
8.0%
|
– |
| 63 |
MiMo-V2.5-Pro (reasoning on)Xiaomi |
8.0%
|
$0.43 / $0.87 |
| 75 |
Qwen3-4B (no reasoning)Alibaba |
9.0%
|
– |
| 75 |
Qwen3.5-122B-A10B (reasoning on)Alibaba |
9.0%
|
$0.26 / $2.08 |
| 75 |
Qwen3.6-27B (no reasoning)Alibaba |
9.0%
|
$0.30 / $3.20 |
| 75 |
Claude Opus 4.1 (reasoning on)Anthropic |
9.0%
|
$15 / $75 |
| 75 |
Claude Opus 4.8 (high reasoning)Anthropic |
9.0%
|
$5 / $25 |
| 75 |
Claude Opus 4.8 (max reasoning)Anthropic |
9.0%
|
$5 / $25 |
| 75 |
Gemini 3.5 Flash (low reasoning)Google |
9.0%
|
$1.50 / $9 |
| 75 |
Gemini 3.6 Flash (minimal reasoning)Google |
9.0%
|
$1.50 / $7.50 |
| 75 |
Gemini 3.7 Flash (low reasoning)Google |
9.0%
|
$1.50 / $7.50 |
| 75 |
Gemma 3 12BGoogle |
9.0%
|
$0.05 / $0.15 |
| 75 |
Gemma 3 4BGoogle |
9.0%
|
$0.05 / $0.10 |
| 75 |
Gemma 4 E2BGoogle |
9.0%
|
– |
| 75 |
ChatGPT-4o (2025-03-26)OpenAI |
9.0%
|
– |
| 75 |
GLM-5.1 (reasoning on)Z.ai |
9.0%
|
$1.38 / $4.40 |
| 89 |
Qwen3.6-35B-A3B (no reasoning)Alibaba |
10.0%
|
$0.10 / $1 |
| 89 |
Claude 3.7 Sonnet (reasoning on)Anthropic |
10.0%
|
– |
| 89 |
Claude Opus 4.8 (medium reasoning)Anthropic |
10.0%
|
$5 / $25 |
| 89 |
Gemma 4 E2B (reasoning by prefill)Google |
10.0%
|
– |
| 89 |
Gemma 4 E4B (reasoning by prefill)Google |
10.0%
|
– |
| 89 |
Llama 3.3 70B InstructMeta |
10.0%
|
$0.59 / $0.79 |
| 89 |
Kimi K2.5 (reasoning on)Moonshot AI |
10.0%
|
$0.57 / $2.85 |
| 89 |
GPT-5.6 Sol (low reasoning)OpenAI |
10.0%
|
$4 / $20 |
| 89 |
Grok 4.1 Fast (non-reasoning)xAI |
10.0%
|
– |
| 89 |
GLM-4.5-Air (no reasoning)Z.ai |
10.0%
|
$0.14 / $0.86 |
| 99 |
Qwen3.5-27B (reasoning by prefill)Alibaba |
11.0%
|
$0.27 / $2.16 |
| 99 |
Qwen3.6-Plus (no reasoning)Alibaba |
11.0%
|
$0.33 / $1.95 |
| 99 |
Gemini 3.6 Flash (high reasoning)Google |
11.0%
|
$1.50 / $7.50 |
| 99 |
Mistral Large 2 (2407)Mistral AI |
11.0%
|
$2 / $6 |
| 99 |
Mistral Large 2.1 (2411)Mistral AI |
11.0%
|
– |
| 99 |
Mistral Small 3.1 24BMistral AI |
11.0%
|
$0.35 / $0.56 |
| 99 |
Mistral Small (2409)Mistral AI |
11.0%
|
– |
| 106 |
DeepSeek-V4-Flash (0423, reasoning on)DeepSeek |
12.0%
|
$0.14 / $0.28 |
| 106 |
Gemini 3.5 Flash (medium reasoning)Google |
12.0%
|
$1.50 / $9 |
| 106 |
Gemini 3.6 Flash (medium reasoning)Google |
12.0%
|
$1.50 / $7.50 |
| 106 |
GPT-4o (2024-05-13)OpenAI |
12.0%
|
$5 / $15 |
| 106 |
GLM-5.2 (no reasoning)Z.ai |
12.0%
|
$1.40 / $4.40 |
| 111 |
Qwen3-30B-A3B-Instruct-2507Alibaba |
13.0%
|
$0.09 / $0.30 |
| 111 |
Claude Sonnet 4 (reasoning on)Anthropic |
13.0%
|
$3 / $15 |
| 111 |
Gemini 3.5 Flash (minimal reasoning)Google |
13.0%
|
$1.50 / $9 |
| 111 |
Gemini 3.8 Flash (high reasoning)Google |
13.0%
|
$1.50 / $7.50 |
| 111 |
Llama 4 MaverickMeta |
13.0%
|
$0.27 / $0.85 |
| 111 |
GPT-5.5 (extra-high reasoning)OpenAI |
13.0%
|
$5 / $30 |
| 111 |
GLM-4.5 (no reasoning)Z.ai |
13.0%
|
$0.60 / $2.20 |
| 111 |
GLM-4.6 (reasoning on)Z.ai |
13.0%
|
$0.50 / $2 |
| 119 |
Qwen3-30B-A3B (no reasoning)Alibaba |
14.0%
|
$0.12 / $0.50 |
| 119 |
Gemini 3.5 Flash (high reasoning)Google |
14.0%
|
$1.50 / $9 |
| 119 |
Gemini 3.8 Flash (medium reasoning)Google |
14.0%
|
$1.50 / $7.50 |
| 119 |
MedGemma 27B TextGoogle |
14.0%
|
– |
| 119 |
LFM2-24B-A2BLiquid AI |
14.0%
|
– |
| 119 |
Llama 3.1 405B InstructMeta |
14.0%
|
– |
| 119 |
Muse Glimmer 30B (extra-high reasoning)Meta |
14.0%
|
$0.30 / $1.20 |
| 119 |
GPT-5.1 ChatOpenAI |
14.0%
|
– |
| 127 |
Qwen3-235B-A22B-Instruct-2507Alibaba |
15.0%
|
$0.15 / $0.75 |
| 127 |
Qwen3.5-9B (reasoning by prefill)Alibaba |
15.0%
|
$0.10 / $0.15 |
| 127 |
Olmo 3 7B InstructAi2 |
15.0%
|
– |
| 127 |
Claude 3 HaikuAnthropic |
15.0%
|
– |
| 127 |
Gemma 4 E4BGoogle |
15.0%
|
– |
| 127 |
Llama 3.1 70B InstructMeta |
15.0%
|
$0.40 / $0.40 |
| 127 |
Mistral Large 3 (no reasoning)Mistral AI |
15.0%
|
$0.50 / $1.50 |
| 127 |
GPT-5.6 Luna (extra-high reasoning)OpenAI |
15.0%
|
$0.20 / $1.20 |
| 135 |
Qwen3.5-2B (no reasoning)Alibaba |
16.0%
|
– |
| 135 |
Qwen3.5-4B (reasoning by prefill)Alibaba |
16.0%
|
– |
| 135 |
Qwen3.6-35B-A3B (reasoning by prefill)Alibaba |
16.0%
|
$0.10 / $1 |
| 135 |
Qwen3-Coder-30B-A3B-InstructAlibaba |
16.0%
|
$0.07 / $0.28 |
| 135 |
Gemini 3.8 Flash (low reasoning)Google |
16.0%
|
$1.50 / $7.50 |
| 135 |
Gemini 3 Flash Preview (minimal reasoning)Google |
16.0%
|
$0.50 / $3 |
| 135 |
Muse Glimmer 30B (high reasoning)Meta |
16.0%
|
$0.30 / $1.20 |
| 135 |
GPT-5.6 Luna (high reasoning)OpenAI |
16.0%
|
$0.20 / $1.20 |
| 135 |
GPT-5.6 Sol (no reasoning)OpenAI |
16.0%
|
$4 / $20 |
| 135 |
GPT-5 Chat (latest)OpenAI |
16.0%
|
– |
| 135 |
Grok 3xAI |
16.0%
|
– |
| 135 |
MiMo-V2.5 (reasoning on)Xiaomi |
16.0%
|
$0.17 / $0.34 |
| 135 |
GLM-5.1 (no reasoning)Z.ai |
16.0%
|
$1.38 / $4.40 |
| 148 |
Qwen2.5-32B-InstructAlibaba |
17.0%
|
– |
| 148 |
Qwen3.5-2B (reasoning by prefill)Alibaba |
17.0%
|
– |
| 148 |
Qwen3.5-35B-A3B (no reasoning)Alibaba |
17.0%
|
$0.16 / $1.30 |
| 148 |
Qwen3-8B (no reasoning)Alibaba |
17.0%
|
$0.12 / $0.46 |
| 148 |
DeepSeek-V3DeepSeek |
17.0%
|
$0.26 / $1.03 |
| 148 |
Magistral Small 1.2Mistral AI |
17.0%
|
– |
| 148 |
Mistral Small 3.2 24BMistral AI |
17.0%
|
$0.094 / $0.25 |
| 148 |
GPT-5.6 Luna (no reasoning)OpenAI |
17.0%
|
$0.20 / $1.20 |
| 148 |
Falcon-H1 7B InstructTII |
17.0%
|
– |
| 148 |
Grok 4 (0709)xAI |
17.0%
|
– |
| 158 |
Qwen3-0.6B (reasoning on)Alibaba |
18.0%
|
– |
| 158 |
Qwen3.5-35B-A3B (reasoning by prefill)Alibaba |
18.0%
|
$0.16 / $1.30 |
| 158 |
Qwen3.5-4B (no reasoning)Alibaba |
18.0%
|
– |
| 158 |
DeepSeek-R1DeepSeek |
18.0%
|
$0.70 / $2.50 |
| 158 |
Mistral Medium 3.5 (no reasoning)Mistral AI |
18.0%
|
$1.50 / $7.50 |
| 158 |
Mistral NemoMistral AI |
18.0%
|
$0.023 / $0.03 |
| 158 |
Kimi K2.6 (reasoning on)Moonshot AI |
18.0%
|
$0.95 / $4 |
| 158 |
o3 (high reasoning)OpenAI |
18.0%
|
$2 / $8 |
| 158 |
o3 (medium reasoning)OpenAI |
18.0%
|
$2 / $8 |
| 158 |
Hy3 Preview (reasoning on)Tencent |
18.0%
|
$0.18 / $0.60 |
| 158 |
Falcon-H1 3B InstructTII |
18.0%
|
– |
| 158 |
GLM-4.6 (no reasoning)Z.ai |
18.0%
|
$0.50 / $2 |
| 158 |
GLM-5.2 (reasoning on)Z.ai |
18.0%
|
$1.40 / $4.40 |
| 171 |
Qwen2.5-7B-InstructAlibaba |
19.0%
|
$0.10 / $0.20 |
| 171 |
Qwen2.5-14B-InstructAlibaba |
19.0%
|
– |
| 171 |
Qwen3-32B (no reasoning)Alibaba |
19.0%
|
$0.14 / $0.40 |
| 171 |
Qwen3.5-27B (no reasoning)Alibaba |
19.0%
|
$0.27 / $2.16 |
| 171 |
Qwen3-VL-235B-A22B-InstructAlibaba |
19.0%
|
$0.30 / $1.50 |
| 171 |
Qwen3-VL-2B-InstructAlibaba |
19.0%
|
– |
| 171 |
DeepSeek-V4-Flash (0423, no reasoning)DeepSeek |
19.0%
|
$0.14 / $0.28 |
| 171 |
Gemini 2.5 ProGoogle |
19.0%
|
$1.25 / $10 |
| 171 |
Gemini 3.1 Pro Preview (low reasoning)Google |
19.0%
|
$2 / $12 |
| 171 |
Gemini 3.1 Pro Preview (medium reasoning)Google |
19.0%
|
$2 / $12 |
| 171 |
Gemma 2 2BGoogle |
19.0%
|
– |
| 171 |
Llama 4 ScoutMeta |
19.0%
|
$0.18 / $0.59 |
| 171 |
Phi-4Microsoft |
19.0%
|
$0.07 / $0.14 |
| 171 |
GPT-5.6 Luna (low reasoning)OpenAI |
19.0%
|
$0.20 / $1.20 |
| 171 |
o4-mini (high reasoning)OpenAI |
19.0%
|
$1.10 / $4.40 |
| 171 |
Grok 4 Fast (non-reasoning)xAI |
19.0%
|
– |
| 187 |
Jamba Large 1.7AI21 Labs |
20.0%
|
– |
| 187 |
Qwen2.5-1.5B-InstructAlibaba |
20.0%
|
– |
| 187 |
Qwen2.5-VL-3B-InstructAlibaba |
20.0%
|
– |
| 187 |
Qwen3-14B (no reasoning)Alibaba |
20.0%
|
$0.12 / $0.24 |
| 187 |
Qwen3.5-122B-A10B (no reasoning)Alibaba |
20.0%
|
$0.26 / $2.08 |
| 187 |
Claude 3 OpusAnthropic |
20.0%
|
– |
| 187 |
Gemini 2.5 Flash Preview (09-2025, no reasoning)Google |
20.0%
|
– |
| 187 |
Gemini 3.1 Pro Preview (high reasoning)Google |
20.0%
|
$2 / $12 |
| 187 |
Gemma 2 27BGoogle |
20.0%
|
$0.65 / $0.65 |
| 187 |
Llama 3.1 8B InstructMeta |
20.0%
|
$0.05 / $0.08 |
| 187 |
Mistral Medium 3Mistral AI |
20.0%
|
$0.40 / $2 |
| 187 |
Kimi K2 ThinkingMoonshot AI |
20.0%
|
$0.60 / $2.50 |
| 187 |
Kimi Linear 48B A3B InstructMoonshot AI |
20.0%
|
– |
| 187 |
Kimi-VL-A3B-InstructMoonshot AI |
20.0%
|
– |
| 187 |
GPT-5.6 Luna (medium reasoning)OpenAI |
20.0%
|
$0.20 / $1.20 |
| 187 |
Falcon-H1 1.5B Deep InstructTII |
20.0%
|
– |
| 203 |
Qwen2.5-72B-InstructAlibaba |
21.0%
|
$0.36 / $0.40 |
| 203 |
Qwen3.5-9B (no reasoning)Alibaba |
21.0%
|
$0.10 / $0.15 |
| 203 |
Command ACohere |
21.0%
|
$2.50 / $10 |
| 203 |
Mixtral 8x22B InstructMistral AI |
21.0%
|
$2 / $6 |
| 203 |
Grok 4.3xAI |
21.0%
|
$1.25 / $2.50 |
| 203 |
Grok 4.5xAI |
21.0%
|
$2 / $6 |
| 203 |
GLM-4.5 (reasoning on)Z.ai |
21.0%
|
$0.60 / $2.20 |
| 210 |
Llama 3.2 1B InstructMeta |
22.0%
|
$0.027 / $0.20 |
| 210 |
Muse Glimmer 30B (medium reasoning)Meta |
22.0%
|
$0.30 / $1.20 |
| 210 |
Mistral Small 4 (no reasoning)Mistral AI |
22.0%
|
$0.15 / $0.60 |
| 210 |
Kimi K2 (0905)Moonshot AI |
22.0%
|
$0.60 / $2.50 |
| 210 |
Kimi K2 (0711)Moonshot AI |
22.0%
|
$0.57 / $2.30 |
| 210 |
GPT-5.6 Terra (extra-high reasoning)OpenAI |
22.0%
|
$2 / $12 |
| 216 |
Qwen3.5-397B-A17B (no reasoning)Alibaba |
23.0%
|
$0.55 / $3.50 |
| 216 |
Qwen3-MaxAlibaba |
23.0%
|
$0.78 / $3.90 |
| 216 |
Gemini 3 Flash Preview (medium reasoning)Google |
23.0%
|
$0.50 / $3 |
| 216 |
Ministral 3 8BMistral AI |
23.0%
|
$0.15 / $0.15 |
| 216 |
Mistral Large 3 (reasoning on)Mistral AI |
23.0%
|
$0.50 / $1.50 |
| 216 |
Falcon-H1 1.5B InstructTII |
23.0%
|
– |
| 216 |
Grok 4 Fast (reasoning)xAI |
23.0%
|
– |
| 216 |
MiMo-V2.5-Pro (no reasoning)Xiaomi |
23.0%
|
$0.43 / $0.87 |
| 216 |
GLM-4-32B-0414Z.ai |
23.0%
|
– |
| 225 |
Qwen3.5-0.8B (no reasoning)Alibaba |
24.0%
|
– |
| 225 |
Qwen3.6-27B (reasoning by prefill)Alibaba |
24.0%
|
$0.30 / $3.20 |
| 225 |
Claude Haiku 4.5 (reasoning on)Anthropic |
24.0%
|
$1 / $5 |
| 225 |
Trinity Large PreviewArcee AI |
24.0%
|
– |
| 225 |
Gemini 2.5 Flash Preview (09-2025, reasoning on)Google |
24.0%
|
– |
| 225 |
Gemma 2 9BGoogle |
24.0%
|
– |
| 225 |
Ministral 3 14BMistral AI |
24.0%
|
$0.20 / $0.20 |
| 225 |
Kimi K2.5 (no reasoning)Moonshot AI |
24.0%
|
$0.57 / $2.85 |
| 225 |
GPT-5.2 ChatOpenAI |
24.0%
|
– |
| 225 |
o1 (high reasoning)OpenAI |
24.0%
|
$15 / $60 |
| 225 |
Solar 10.7B Instruct v1.0Upstage |
24.0%
|
– |
| 236 |
DeepSeek-V3.2-Exp (reasoning on)DeepSeek |
25.0%
|
$0.27 / $0.41 |
| 236 |
DeepSeek-V3.2-SpecialeDeepSeek |
25.0%
|
– |
| 236 |
LFM2-8B-A1BLiquid AI |
25.0%
|
– |
| 236 |
Muse Glimmer 30B (low reasoning)Meta |
25.0%
|
$0.30 / $1.20 |
| 236 |
Grok 4.6xAI |
25.0%
|
$2 / $6 |
| 241 |
Qwen3-1.7B (reasoning on)Alibaba |
26.0%
|
– |
| 241 |
Qwen3-VL-32B-InstructAlibaba |
26.0%
|
$0.10 / $0.42 |
| 241 |
DeepSeek-V3.2 (no reasoning)DeepSeek |
26.0%
|
$0.30 / $0.96 |
| 241 |
Gemini 3 Flash Preview (high reasoning)Google |
26.0%
|
$0.50 / $3 |
| 241 |
Devstral Small 2Mistral AI |
26.0%
|
– |
| 241 |
InternLM3 8B InstructShanghai AI Lab |
26.0%
|
– |
| 247 |
DeepSeek-V3.2-Exp (no reasoning)DeepSeek |
27.0%
|
$0.27 / $0.41 |
| 247 |
Mistral Medium 3.1Mistral AI |
27.0%
|
$0.40 / $2 |
| 247 |
Mixtral 8x7B Instruct v0.1Mistral AI |
27.0%
|
– |
| 247 |
o4-mini (medium reasoning)OpenAI |
27.0%
|
$1.10 / $4.40 |
| 251 |
Qwen3-Omni-30B-A3B-ThinkingAlibaba |
28.0%
|
– |
| 251 |
Qwen3-VL-8B-InstructAlibaba |
28.0%
|
$0.12 / $0.46 |
| 251 |
Command R+ (08-2024)Cohere |
28.0%
|
$2.50 / $10 |
| 251 |
Nemotron Nano 12B v2 VL (BF16, no reasoning)NVIDIA |
28.0%
|
– |
| 251 |
Grok 4.7xAI |
28.0%
|
$2 / $6 |
| 251 |
GLM-4.7 (no reasoning)Z.ai |
28.0%
|
$0.54 / $1.98 |
| 257 |
Qwen2.5-VL-72B-InstructAlibaba |
29.0%
|
$0.80 / $1 |
| 257 |
Llama 3.3 8B InstructAllura Forge |
29.0%
|
– |
| 257 |
DeepSeek-V3.2 (reasoning on)DeepSeek |
29.0%
|
$0.30 / $0.96 |
| 257 |
o3 (low reasoning)OpenAI |
29.0%
|
$2 / $8 |
| 257 |
MiMo-V2.5 (no reasoning)Xiaomi |
29.0%
|
$0.17 / $0.34 |
| 262 |
Qwen3-235B-A22B-Thinking-2507Alibaba |
30.0%
|
$0.30 / $3 |
| 262 |
Qwen3-VL-235B-A22B-ThinkingAlibaba |
30.0%
|
$0.40 / $4 |
| 262 |
DeepSeek-V3.1 (no reasoning)DeepSeek |
30.0%
|
$0.55 / $1.65 |
| 262 |
Ministral 3 8B ReasoningMistral AI |
30.0%
|
– |
| 262 |
GPT-5.4 (extra-high reasoning)OpenAI |
30.0%
|
$2.50 / $15 |
| 267 |
Command R (08-2024)Cohere |
31.0%
|
$0.15 / $0.60 |
| 267 |
Llama 3.2 3B InstructMeta |
31.0%
|
$0.05 / $0.33 |
| 267 |
MiniMax-M2.1MiniMax |
31.0%
|
$0.30 / $1.20 |
| 267 |
GPT-5.6 Terra (high reasoning)OpenAI |
31.0%
|
$2 / $12 |
| 267 |
GPT-5.6 Terra (medium reasoning)OpenAI |
31.0%
|
$2 / $12 |
| 272 |
Qwen3-1.7B (no reasoning)Alibaba |
32.0%
|
– |
| 272 |
DeepSeek-V3-0324DeepSeek |
32.0%
|
$0.25 / $1 |
| 272 |
DeepSeek-V3.1-Terminus (reasoning on)DeepSeek |
32.0%
|
$0.27 / $1 |
| 272 |
Hy3 Preview (no reasoning)Tencent |
32.0%
|
$0.18 / $0.60 |
| 276 |
Gemini 3 Pro Preview (low reasoning)Google |
33.0%
|
– |
| 276 |
GLM-4.7 (reasoning on)Z.ai |
33.0%
|
$0.54 / $1.98 |
| 278 |
Qwen2.5-Coder-7B-InstructAlibaba |
34.0%
|
– |
| 278 |
DeepSeek-V3.1 (reasoning on)DeepSeek |
34.0%
|
$0.55 / $1.65 |
| 278 |
DeepSeek-V3.1-Terminus (no reasoning)DeepSeek |
34.0%
|
$0.27 / $1 |
| 278 |
DeepSeek-V4-Pro (0423, reasoning on)DeepSeek |
34.0%
|
$1.42 / $2.83 |
| 278 |
Gemini 3 Pro Preview (high reasoning)Google |
34.0%
|
– |
| 278 |
Mistral Small 4 (high reasoning)Mistral AI |
34.0%
|
$0.15 / $0.60 |
| 278 |
Kimi K2.6 (no reasoning)Moonshot AI |
34.0%
|
$0.95 / $4 |
| 278 |
GLM-5 (reasoning on)Z.ai |
34.0%
|
$0.95 / $2.55 |
| 286 |
Ministral 3 8B (reasoning by prefill)Mistral AI |
35.0%
|
$0.15 / $0.15 |
| 286 |
Nemotron 3 Nano 30B A3BNVIDIA |
35.0%
|
$0.05 / $0.20 |
| 286 |
GPT-5.6 Terra (low reasoning)OpenAI |
35.0%
|
$2 / $12 |
| 286 |
GLM-4.6V (reasoning on)Z.ai |
35.0%
|
$0.30 / $0.90 |
| 290 |
Jamba Mini 1.7AI21 Labs |
36.0%
|
– |
| 290 |
MiniMax-M2.7MiniMax |
36.0%
|
$0.30 / $1.20 |
| 290 |
o1 (low reasoning)OpenAI |
36.0%
|
$15 / $60 |
| 290 |
o4-mini (low reasoning)OpenAI |
36.0%
|
$1.10 / $4.40 |
| 290 |
Grok 4.20 (0309, non-reasoning)xAI |
36.0%
|
– |
| 290 |
GLM-5 (no reasoning)Z.ai |
36.0%
|
$0.95 / $2.55 |
| 296 |
Grok 4.20 Beta (0309, non-reasoning)xAI |
37.0%
|
– |
| 297 |
Inflection 3 ProductivityInflection AI |
38.0%
|
– |
| 297 |
Grok 4.20 Multi-Agent Beta (0309, 4 agents)xAI |
38.0%
|
– |
| 299 |
GLM-4.7-Flash (no reasoning)Z.ai |
39.0%
|
$0.06 / $0.40 |
| 300 |
Qwen3-VL-4B-InstructAlibaba |
40.0%
|
– |
| 300 |
Llama 2 70B ChatMeta |
40.0%
|
– |
| 300 |
Falcon-H1 0.5B InstructTII |
40.0%
|
– |
| 303 |
MiniMax-M2.5MiniMax |
41.0%
|
$0.30 / $1.20 |
| 304 |
Ring-1TAnt Group |
42.0%
|
– |
| 304 |
DeepSeek-V4-Pro (0423, no reasoning)DeepSeek |
42.0%
|
$1.42 / $2.83 |
| 304 |
Inflection 3 PiInflection AI |
42.0%
|
– |
| 304 |
GPT-5.5 (high reasoning)OpenAI |
42.0%
|
$5 / $30 |
| 304 |
GPT-5.6 Terra (no reasoning)OpenAI |
42.0%
|
$2 / $12 |
| 304 |
Step 3.5 FlashStepFun |
42.0%
|
$0.10 / $0.30 |
| 304 |
MiMo-V2-Flash (reasoning on)Xiaomi |
42.0%
|
– |
| 311 |
Rnj-1 InstructEssential AI |
43.0%
|
– |
| 311 |
Grok 4.20 Beta (0309, reasoning)xAI |
43.0%
|
– |
| 313 |
Ministral 3 14B ReasoningMistral AI |
44.0%
|
– |
| 313 |
MiMo-V2-Flash (no reasoning)Xiaomi |
44.0%
|
– |
| 315 |
Nova 2 Lite (reasoning on)Amazon |
45.0%
|
$0.30 / $2.50 |
| 315 |
DeepSeek-R1-0528DeepSeek |
45.0%
|
$0.50 / $2.18 |
| 317 |
Nova 2 Lite (no reasoning)Amazon |
46.0%
|
$0.30 / $2.50 |
| 317 |
GPT-5.4 (high reasoning)OpenAI |
46.0%
|
$2.50 / $15 |
| 317 |
Grok 4.20 (0309, reasoning)xAI |
46.0%
|
– |
| 320 |
Granite 4.0 H SmallIBM |
47.0%
|
– |
| 321 |
EXAONE 4.0 32BLG AI Research |
50.0%
|
– |
| 321 |
GPT-5.4 (no reasoning)OpenAI |
50.0%
|
$2.50 / $15 |
| 323 |
Qwen3-14B (reasoning on)Alibaba |
53.0%
|
$0.12 / $0.24 |
| 323 |
GPT-5.4 (medium reasoning)OpenAI |
53.0%
|
$2.50 / $15 |
| 325 |
Reka Flash 3Reka AI |
54.0%
|
$0.10 / $0.20 |
| 326 |
Apriel Nemotron 15B ThinkerServiceNow |
56.0%
|
– |
| 327 |
GPT-5.4 (low reasoning)OpenAI |
57.0%
|
$2.50 / $15 |
| 328 |
Qwen3-30B-A3B (reasoning on)Alibaba |
58.0%
|
$0.12 / $0.50 |
| 328 |
Ministral 3 14B (reasoning by prefill)Mistral AI |
58.0%
|
$0.20 / $0.20 |
| 328 |
GPT-5 (high reasoning)OpenAI |
58.0%
|
$1.25 / $10 |
| 331 |
Seed-OSS-36B-Instruct (no reasoning)ByteDance |
59.0%
|
– |
| 332 |
Mistral Medium 3.5 (high reasoning)Mistral AI |
60.0%
|
$1.50 / $7.50 |
| 333 |
GLM-4.5-AirZ.ai |
61.0%
|
$0.14 / $0.86 |
| 334 |
Qwen3-4B (reasoning on)Alibaba |
62.0%
|
– |
| 335 |
Qwen2.5-VL-32B-InstructAlibaba |
64.0%
|
– |
| 335 |
Qwen3-4B-Thinking-2507Alibaba |
64.0%
|
– |
| 335 |
Qwen3-8B (reasoning on)Alibaba |
64.0%
|
$0.12 / $0.46 |
| 338 |
Qwen3-Next-80B-A3B-ThinkingAlibaba |
67.0%
|
$0.15 / $1.20 |
| 339 |
Kimi-VL-A3B-Thinking (2506)Moonshot AI |
71.0%
|
– |
| 339 |
GPT-5.5 (medium reasoning)OpenAI |
71.0%
|
$5 / $30 |
| 341 |
MiniMax-M2MiniMax |
73.0%
|
$0.30 / $1.20 |
| 342 |
Qwen3-32B (reasoning on)Alibaba |
74.0%
|
$0.14 / $0.40 |
| 343 |
GPT-5.2 (high reasoning)OpenAI |
76.0%
|
$1.75 / $14 |
| 344 |
Qwen3-VL-4B-ThinkingAlibaba |
79.0%
|
– |
| 345 |
Nemotron Nano 12B v2 VL (BF16)NVIDIA |
81.0%
|
– |
| 346 |
Qwen3-30B-A3B-Thinking-2507Alibaba |
82.0%
|
$0.20 / $2.40 |
| 346 |
QwQ-32BAlibaba |
82.0%
|
– |
| 346 |
Ministral 3 8B Reasoning (reasoning by prefill)Mistral AI |
82.0%
|
– |
| 349 |
GLM-4.6V (no reasoning)Z.ai |
86.0%
|
$0.30 / $0.90 |
| 350 |
Qwen3-VL-2B-ThinkingAlibaba |
87.0%
|
– |
| 351 |
Qwen3-VL-8B-ThinkingAlibaba |
89.0%
|
$0.18 / $2.10 |
| 352 |
Qwen3-VL-32B-ThinkingAlibaba |
91.0%
|
– |
| 353 |
GPT-5 (low reasoning)OpenAI |
92.0%
|
$1.25 / $10 |
| 354 |
GPT-5.2 (medium reasoning)OpenAI |
93.0%
|
$1.75 / $14 |
| 355 |
GPT-5.5 (low reasoning)OpenAI |
96.0%
|
$5 / $30 |
| 356 |
GPT-5.5 (no reasoning)OpenAI |
98.0%
|
$5 / $30 |
| 356 |
gpt-oss-20b (low reasoning)OpenAI |
98.0%
|
$0.03 / $0.15 |
| 358 |
Olmo 3 32B ThinkAi2 |
102.0%
|
– |
| 359 |
Nanbeige4-3B-Thinking (2510)Nanbeige |
103.0%
|
– |
| 359 |
GPT-5.2 (low reasoning)OpenAI |
103.0%
|
$1.75 / $14 |
| 361 |
Seed-OSS-36B-Instruct (512-token reasoning budget)ByteDance |
104.0%
|
– |
| 362 |
gpt-oss-120b (medium reasoning)OpenAI |
107.0%
|
$0.15 / $0.60 |
| 363 |
Solar Pro 3Upstage |
108.0%
|
$0.15 / $0.60 |
| 364 |
GPT-5.2 (no reasoning)OpenAI |
112.0%
|
$1.75 / $14 |
| 365 |
Qwen3-VL-30B-A3B-ThinkingAlibaba |
113.0%
|
$0.29 / $1 |
| 365 |
GPT-5.1 (high reasoning)OpenAI |
113.0%
|
$1.25 / $10 |
| 367 |
Olmo 3 7B ThinkAi2 |
117.0%
|
– |
| 368 |
Ling-1TAnt Group |
120.0%
|
– |
| 369 |
Ministral 3 14B Reasoning (reasoning by prefill)Mistral AI |
123.0%
|
– |
| 370 |
GPT-5.1 (medium reasoning)OpenAI |
129.0%
|
$1.25 / $10 |
| 371 |
GPT-5.1 (low reasoning)OpenAI |
157.0%
|
$1.25 / $10 |
| 372 |
Seed-OSS-36B-InstructByteDance |
162.0%
|
– |
| 373 |
GLM-4.7-Flash (reasoning by prefill)Z.ai |
172.0%
|
$0.06 / $0.40 |
| 374 |
Nanbeige4-3B-Thinking (2511)Nanbeige |
173.0%
|
– |
| 375 |
gpt-oss-20b (medium reasoning)OpenAI |
186.0%
|
$0.03 / $0.15 |
| 376 |
Magistral Small 1.2 (reasoning by system prompt)Mistral AI |
197.0%
|
– |
| 377 |
Ministral 3 8B Reasoning (reasoning by system prompt)Mistral AI |
224.0%
|
– |
| 378 |
Nemotron 3 Nano 30B A3B (reasoning by prefill)NVIDIA |
251.0%
|
$0.05 / $0.20 |
| 379 |
gpt-oss-20b (high reasoning)OpenAI |
282.0%
|
$0.03 / $0.15 |
