Podnami

Best performance on Podnami

LLM Rankings

Models from Settings → AI Selection, scored for live co-hosts: speed (TTFT), reliability, conversation quality (CQ), and credit value. High speed alone does not mean high CQ.

Last completed run: 2026-11-13T02:10:04.501853+00:00 · 22 models

Click a column header to sort.

Ranked models

# Model Stars Overall Speed Reliability CQ ? CQ — Conversation Quality
Suitability for Podnami live co-hosts: tool calling, no speaker-label leaks, handoffs, short memory, spoken brevity, an in-character chat check, plus whether the model is a non-thinking chat-oriented model vs a utility/doc or heavy-reasoning model. 		Value TTFT p50 Tier Badges
1 –
Gemini 2.5 Lite
Google · google/gemini-2.5-flash-lite
🔒 10 runs at #1
★★★★★ 99.4 100 100 99 100 0.39s Budget Best value
2 ▲1
Ministral 14b-2512
Ministral 14b-2512 · mistralai/ministral-14b-2512
▲ best #1
★★★★★ 97.7 100 100 95 98 0.43s Budget
3 ▲10
Mistral Nemo
Mistral · mistralai/mistral-nemo
▲ best #1
★★★★★ 95.7 95 100 94 96 0.71s Budget Not recommended for live co-hosts
4 ▲4
Amazon Nova Lite V1
Amazon · amazon/nova-lite-v1
▲ best #3
★★★★★ 94.9 100 100 89 96 0.43s Budget
5 –
Claude Haiku 4.5
Anthropic · anthropic/claude-haiku-4.5
🔒 2 runs at #5 ▲ best #3
★★★★★ 94.2 95 100 99 73 0.77s Standard
6 –
Google Gemini Flash Lite 3.5
Google · google/gemini-3.5-flash-lite
🔒 2 runs at #6 ▲ best #3
★★★★★ 94.0 100 100 95 74 0.59s Standard
7 ▲2
DeepSeek Chat
DeepSeek · deepseek/deepseek-chat
▲ best #1
★★★★★ 93.1 80 100 99 91 0.73s Budget
8 ▲4
Gemma 4 31B IT
Google · google/gemma-4-31b-it
▲ best #1
★★★★★ 93.1 80 100 99 91 0.44s Budget
9 ▲1
DeepSeek V4 Flash
DeepSeek · deepseek/deepseek-v4-flash
▲ best #4
★★★★★ 93.1 80 100 99 91 0.34s Budget
10 ▲1
DeepseekV32
DeepSeek · deepseek/deepseek-v3.2
▲ best #2
★★★★★ 91.4 80 100 95 89 0.47s Budget
11 ▼9
Meta Llamma Scout
Meta Llamma Scout · meta-llama/llama-4-scout
▲ best #1
★★★★★ 91.4 80 100 95 89 0.24s Budget
12 ▼5
Inclusion Ling 3.0 Flash
Inclusion · inclusionai/ling-3.0-flash
▲ best #1
★★★★★ 91.2 95 86 91 92 1.16s Budget
13 ▼9
GPT-4o Mini
OpenAI · openai/gpt-4o-mini
▲ best #3
★★★★★ 89.7 80 100 99 68 0.71s Standard
14 –
Step 3.5 Flash
StepFun · stepfun/step-3.5-flash
🔒 7 runs at #14 ▲ best #12
★★★★☆ 74.7 80 72 72 76 2.36s Budget
15 –
Inclusion Ling 2.6 Flash
Ling · inclusionai/ling-2.6-flash
🔒 2 runs at #15
★☆☆☆☆ 10.8 0 0 24 8 — Budget No endpoint
16 –
Qwen 3.7 Flash
OpenRouter · qwen/qwen3.7-flash
🔒 2 runs at #16 ▲ best #14
★☆☆☆☆ 10.8 0 0 24 8 — Budget Unstable
17 –
Claude 3 Haiku
Anthropic · anthropic/claude-3-haiku
🔒 21 runs at #17
★☆☆☆☆ 10.4 0 0 24 6 — Standard No endpoint
18 –
GPT-4 Turbo
OpenAI · openai/gpt-4-turbo
🔒 21 runs at #18 ▲ best #10
★☆☆☆☆ 10.2 0 0 24 5 — Premium No endpoint
19 –
Incllusion Ling 2.6
Inclusion · inclusionai/ling-2.6-1t
🔒 21 runs at #19
★☆☆☆☆ 9.1 0 0 20 7 — Budget No endpoint
20 –
GPT-3.5 Turbo
OpenAI · openai/gpt-3.5-turbo
🔒 21 runs at #20 ▲ best #5
★☆☆☆☆ 8.8 0 0 20 5 — Standard No endpoint

Free options (comparison)

# Model Stars Overall Speed Reliability CQ ? CQ — Conversation Quality
Suitability for Podnami live co-hosts: tool calling, no speaker-label leaks, handoffs, short memory, spoken brevity, an in-character chat check, plus whether the model is a non-thinking chat-oriented model vs a utility/doc or heavy-reasoning model. 		Value TTFT p50 Tier Badges
1 –
FREE LLM
OpenRouter · free-llm-cycler
🔒 2 runs at #1
★★★☆☆ 65.8 80 52 62 68 1.36s Free Free option
2 –
Free LLM Router
Open Router · openrouter/free
🔒 2 runs at #2 ▲ best #1
★★★☆☆ 65.2 80 53 61 68 1.11s Free Free option Unstable

▲/▼ = rank change since the previous run · – = no change · NEW = first appearance

Probes are scripted OpenRouter checks (not live mixer sessions). Pass/fail + timings only — no reply transcripts stored. Scores reflect a sampled run (a few attempts per model at a non-zero temperature), so small differences between runs are normal — treat close scores as ties, not regressions.