AI model
performance
report
A concise view of coding completion, cost efficiency, model popularity, and inference provider reliability across the Kilo ecosystem.
- Published
- November 15, 2026
- Benchmark
- Terminal Bench 2.0
- Inference window
- Latest weekly snapshot
KiloBench leaders
Models are ranked by completion rate on Terminal Bench 2.0. Cost per attempt is the observed average for a complete benchmark attempt, including unsuccessful attempts.
| # | Model | Provider | Completion rate | Cost / attempt |
|---|---|---|---|---|
| 1 | GPT-6 Astra ($$$$) 5 attempts | openai | 79.3% | $107.29 |
| 2 | GPT-5.6 Sol 5 attempts | openai | 76.2% | $87.41 |
| 3 | Claude Fable 5.1 ($$$$) 5 attempts | anthropic | 76.2% | $91.41 |
| 4 | DeepSeek V4.1 Flash 5 attempts | deepseek | 75.3% | $2.58 |
| 5 | Gemini 3.8 Flash 5 attempts | 75.3% | $112.27 | |
| 6 | GPT-5.5 5 attempts | openai | 74.2% | $72.63 |
| 7 | Grok 4.6 5 attempts | x-ai | 73.0% | $33.83 |
| 8 | Kimi K3 5 attempts | moonshotai | 72.8% | $48.38 |
| 9 | Claude Opus 5 5 attempts | anthropic | 71.5% | $113.54 |
| 10 | Claude Fable 5 ($$$$) 5 attempts | anthropic | 71.0% | $87.52 |
Inference market view
The 20 most-used models are ranked by token volume from the latest Kilo Gateway weekly snapshot. Primary-provider metrics describe the provider carrying the largest traffic share for each model.
| # | Model | Primary provider | Usage volume | Cost / request | Success rate |
|---|---|---|---|---|---|
| 1 | nemotron-3.5-super-vl:free 1 provider | NVIDIA | 2.1T | $0 | 95.85% |
| 2 | nemotron-3-ultra-550b-a55b:free 1 provider | NVIDIA | 1.6T | $0 | 94.81% |
| 3 | ernie-5.5-flash-preview:free 1 provider | Baidu | 853.9B | $0 | 96.24% |
| 4 | dots-3-note-preview:free 1 provider | Atlas Cloud | 504.4B | $0 | 87.22% |
| 5 | deepseek-v4.1-flash-1017 11 providers | Novita AI | 490.1B | $0.0028 | 97.26% |
| 6 | glyph-cluster 1 provider | Stealth | 314.1B | $0 | 95.33% |
| 7 | beam-free 1 provider | Reflection | 201.6B | $0 | 94.28% |
| 8 | nemotron-3.5-lightning:free 1 provider | NVIDIA | 130.6B | $0 | 85.62% |
| 9 | particle-1:free 1 provider | Particle AI | 129.2B | $0 | 97.23% |
| 10 | openrouter/free 11 providers | NVIDIA | 108.4B | $0 | 87.42% |
Inference market view / continued
The 20 most-used models are ranked by token volume from the latest Kilo Gateway weekly snapshot. Primary-provider metrics describe the provider carrying the largest traffic share for each model.
| # | Model | Primary provider | Usage volume | Cost / request | Success rate |
|---|---|---|---|---|---|
| 11 | deepseek-v4.1-flash 4 providers | Novita AI | 76.9B | $0.0025 | 99.77% |
| 12 | claude-opus-5.5 4 providers | 74.4B | $0.18 | 99.50% | |
| 13 | north-mini-code:free 1 provider | Cohere | 64.6B | $0 | 81.63% |
| 14 | gpt-6-luna 4 providers | OpenAI | 61.8B | $0.0037 | 99.95% |
| 15 | glm-5.3-flash 7 providers | FriendliAI | 56.4B | $0.0062 | 99.05% |
| 16 | gpt-6.1-terra 3 providers | OpenAI | 39.2B | $0.0192 | 99.97% |
| 17 | gpt-6.1-sol 4 providers | OpenAI | 33.4B | $0.0575 | 99.95% |
| 18 | claude-sonnet-5.5 4 providers | 29.2B | $0.0662 | 99.15% | |
| 19 | nemotron-3-nano-omni-30b-a3b-reasoning:free 1 provider | NVIDIA | 26.6B | $0 | 78.26% |
| 20 | crouton-alpha 1 provider | Stealth | 19.7B | $0 | 96.62% |
Cost and reliability
Provider-level traffic share, average request cost, and success rate for the ten most-used models. Traffic share uses the percentage published by Kilo Gateway.
nemotron-3.5-super-vl:free
| Provider | Traffic share | Cost / request | Success rate |
|---|---|---|---|
| NVIDIA | 100.00% | $0 | 95.85% |
nemotron-3-ultra-550b-a55b:free
| Provider | Traffic share | Cost / request | Success rate |
|---|---|---|---|
| NVIDIA | 100.00% | $0 | 94.81% |
ernie-5.5-flash-preview:free
| Provider | Traffic share | Cost / request | Success rate |
|---|---|---|---|
| Baidu | 100.00% | $0 | 96.24% |
dots-3-note-preview:free
| Provider | Traffic share | Cost / request | Success rate |
|---|---|---|---|
| Atlas Cloud | 100.00% | $0 | 87.22% |
Cost and reliability
Provider-level traffic share, average request cost, and success rate for the ten most-used models. Traffic share uses the percentage published by Kilo Gateway.
deepseek-v4.1-flash-1017
| Provider | Traffic share | Cost / request | Success rate |
|---|---|---|---|
| Novita AI | 70.25% | $0.0028 | 97.26% |
| Alibaba | 23.98% | $0.0060 | 99.83% |
| Baseten | 3.44% | $0.0042 | 99.97% |
| Together AI | 1.49% | $0.0033 | 100.00% |
| Fireworks AI | 0.42% | $0.0091 | 99.84% |
| DeepInfra | 0.23% | $0.00041 | 99.99% |
| Parasail | 0.05% | $0.0099 | 99.94% |
| Subconscious | 0.04% | $0.0056 | 100.00% |
| DigitalOcean | 0.04% | $0.0146 | 99.92% |
| Relace | 0.04% | $0.0021 | 99.79% |
| Wafer | 0.02% | $0.0166 | 100.00% |
glyph-cluster
| Provider | Traffic share | Cost / request | Success rate |
|---|---|---|---|
| Stealth | 100.00% | $0 | 95.33% |
Cost and reliability
Provider-level traffic share, average request cost, and success rate for the ten most-used models. Traffic share uses the percentage published by Kilo Gateway.
beam-free
| Provider | Traffic share | Cost / request | Success rate |
|---|---|---|---|
| Reflection | 100.00% | $0 | 94.28% |
nemotron-3.5-lightning:free
| Provider | Traffic share | Cost / request | Success rate |
|---|---|---|---|
| NVIDIA | 100.00% | $0 | 85.62% |
particle-1:free
| Provider | Traffic share | Cost / request | Success rate |
|---|---|---|---|
| Particle AI | 100.00% | $0 | 97.23% |
Cost and reliability
Provider-level traffic share, average request cost, and success rate for the ten most-used models. Traffic share uses the percentage published by Kilo Gateway.
openrouter/free
| Provider | Traffic share | Cost / request | Success rate |
|---|---|---|---|
| NVIDIA | 53.05% | $0 | 87.42% |
| Atlas Cloud | 15.41% | $0 | 87.09% |
| Recursive | 10.40% | $0 | 85.81% |
| Cohere | 6.30% | $0 | 83.93% |
| Baidu | 5.70% | $0 | 89.27% |
| Particle AI | 4.68% | $0 | 91.59% |
| Liquid | 2.08% | $0 | 60.62% |
| Phala | 1.27% | $0 | 85.78% |
| Novita AI | 0.80% | $0 | 85.58% |
| Thinking Machines | 0.16% | $0 | 78.44% |
| Ant Digital | 0.15% | $0 | 89.02% |