This page uses opencode/big-pickle as the comparison baseline. Every chart and table below is intended to answer the same question: where this model leads, where it lags, and what it costs in quality, time, and request pressure.
These charts use opencode/big-pickle as zero. Positive bars mean other models are above the baseline on that metric; negative bars mean they trail it.
Use this to decide whether another model beats opencode/big-pickle enough to justify the change.
| Model | Composite | Delta vs baseline | Success | Success delta | ORPT | ORPT delta | Cost | Cost delta | Wall time |
|---|---|---|---|---|---|---|---|---|---|
| opencode/gpt-5.4-nano | 0.789 | +0.174 | 85% | +19% | 15.17 | -0.21 | $0.4215 | +$0.4215 | 27m 33s |
| opencode/kimi-k2.5 | 0.785 | +0.169 | 89% | +22% | 14.25 | -1.14 | $0.9122 | +$0.9122 | 41m 05s |
| opencode/claude-opus-4-6 | 0.67 | +0.055 | 89% | +22% | 14.88 | -0.51 | $21.8757 | +$21.8757 | 40m 04s |
| opencode/glm-5 | 0.623 | +0.008 | 78% | +11% | 11.57 | -3.82 | $6.4339 | +$6.4339 | 20m 10s |
| opencode/big-pickle Baseline | 0.615 | +0.0 | 67% | +0% | 15.39 | +0.00 | $0.0000 | +$0.0000 | 36m 28s |
| opencode/gpt-5.4 | 0.609 | -0.006 | 78% | +11% | 11.00 | -4.39 | $8.9827 | +$8.9827 | 32m 47s |
| opencode/claude-sonnet-4-6 | 0.593 | -0.022 | 78% | +11% | 16.43 | +1.04 | $11.8406 | +$11.8406 | 42m 31s |
| opencode/glm-5.1 | 0.547 | -0.068 | 67% | +0% | 12.06 | -3.33 | $1.8816 | +$1.8816 | 64m 39s |
| opencode/minimax-m2.5 | 0.481 | -0.134 | 56% | -11% | 18.87 | +3.48 | $0.6413 | +$0.6413 | 32m 15s |
| opencode/gpt-5.4-mini | 0.425 | -0.19 | 48% | -19% | 9.54 | -5.85 | $1.0606 | +$1.0606 | 21m 48s |
| opencode/minimax-m2.5-free | 0.415 | -0.2 | 59% | -7% | 16.19 | +0.80 | $0.0000 | +$0.0000 | 41m 34s |
| opencode/gemini-3-flash | 0.415 | -0.2 | 59% | -7% | 21.81 | +6.42 | $2.4307 | +$2.4307 | 62m 52s |
| opencode/gemini-3.1-pro | 0.291 | -0.324 | 37% | -30% | 12.70 | -2.69 | $5.8536 | +$5.8536 | 51m 25s |
| opencode/nemotron-3-super-free | 0.181 | -0.434 | 26% | -41% | 19.43 | +4.04 | $0.0000 | +$0.0000 | 109m 00s |
This table puts the most revealing tasks first: unsolved tasks, single-solver tasks, and tasks where the baseline trails the winner by a meaningful margin.
| Task | Field read | Baseline result | Winner | Gap to winner | Baseline cost | Baseline time |
|---|---|---|---|---|---|---|
| SELinux registry volume label repair | Clear separation | failed | opencode/kimi-k2.5 1.0 |
1.0 | n/a | 1m 07s |
| Kubernetes rollout repair | Clear separation | failed | opencode/gpt-5.4-mini 1.0 |
1.0 | n/a | 59s |
| Bootstrap phase validation repair | Competitive split | failed | opencode/kimi-k2.5 0.993 |
0.993 | n/a | 2m 08s |
| nftables router ingress repair | Competitive split | failed | opencode/gpt-5.4-nano 0.98 |
0.98 | n/a | 52s |
| Docker Compose observability fix | Competitive split | failed | opencode/gpt-5.4-nano 0.975 |
0.975 | n/a | 45s |
| Kubernetes OIDC RBAC repair | Competitive split | failed | opencode/gpt-5.4-nano 0.95 |
0.95 | n/a | 1m 36s |
| Log audit shell script | Competitive split | dnf | opencode/gpt-5.4-nano 0.935 |
0.935 | n/a | 1m 15s |
| Workspace runtime access convergence | Competitive split | failed | opencode/gpt-5.4-nano 0.932 |
0.932 | n/a | 2m 26s |
| Traefik forwarded header trust repair | Competitive split | failed | opencode/kimi-k2.5 0.913 |
0.913 | n/a | 21s |
| Terraform static site repair | Competitive split | passed | opencode/kimi-k2.5 0.978 |
0.172 | n/a | 2m 45s |
| RHEL k3s node preparation repair | Competitive split | passed | opencode/gpt-5.4-nano 1.0 |
0.143 | n/a | 2m 19s |
| Build workspace plane convergence | Competitive split | passed | opencode/gpt-5.4-nano 0.942 |
0.091 | n/a | 2m 27s |
| ExternalDNS RFC2136 repair | Competitive split | passed | opencode/kimi-k2.5 0.982 |
0.089 | n/a | 1m 54s |
| RHEL NetworkManager bridge VLAN repair | Competitive split | passed | opencode/gpt-5.4-nano 0.951 |
0.081 | n/a | 1m 06s |
| RHEL edge firewalld router repair | Competitive split | passed | opencode/gpt-5.4-nano 0.953 |
0.065 | n/a | 1m 43s |
| Pre-ArgoCD bootstrap sequencing | Competitive split | passed | opencode/gpt-5.4-nano 0.967 |
0.035 | n/a | 4m 23s |
| AppArmor dnsmasq profile repair | Competitive split | passed | opencode/gpt-5.4-nano 0.918 |
0.033 | n/a | 1m 22s |
| Wildcard TLS route coverage | Competitive split | passed | opencode/kimi-k2.5 0.929 |
0.004 | n/a | 1m 08s |
| MetalLB ingress address pool repair | Competitive split | passed | opencode/gpt-5.4-nano 0.928 |
0.001 | n/a | 57s |
| K3s registry mirror trust repair | Competitive split | passed | opencode/big-pickle 1.0 |
0.0 | n/a | 17s |
| Event status shell summary | Competitive split | passed | opencode/big-pickle 1.0 |
0.0 | n/a | 17s |
| Workspace transplant bundle repair | Competitive split | passed | opencode/big-pickle 0.985 |
0.0 | n/a | 25s |
| CNPG restore manifest repair | Competitive split | passed | opencode/big-pickle 0.964 |
0.0 | n/a | 37s |
| Ansible nginx role completion | Competitive split | passed | opencode/big-pickle 0.963 |
0.0 | n/a | 43s |
| Log level rollup shell script | Competitive split | passed | opencode/big-pickle 0.965 |
0.0 | n/a | 54s |
| GitOps workspace render validation | Competitive split | passed | opencode/big-pickle 0.941 |
0.0 | n/a | 1m 09s |
| MCP OpenBao contract repair | Competitive split | passed | opencode/big-pickle 0.954 |
0.0 | n/a | 33s |
Pairwise task wins and top-line deltas show whether a challenger truly beats the baseline or just looks cheaper or faster in isolation.
| Challenger | Task record | Composite edge | Success edge | Cost edge | Time edge | ORPT edge |
|---|---|---|---|---|---|---|
| opencode/nemotron-3-super-free | 18-0 9 ties |
+0.434 | +41% | +$0.0000 | -72m 32s | -4.04 |
| opencode/gemini-3.1-pro | 17-3 7 ties |
+0.324 | +30% | -$5.8536 | -14m 57s | +2.69 |
| opencode/minimax-m2.5-free | 18-4 5 ties |
+0.2 | +7% | +$0.0000 | -5m 05s | -0.80 |
| opencode/gemini-3-flash | 18-5 4 ties |
+0.2 | +7% | -$2.4307 | -26m 23s | -6.42 |
| opencode/gpt-5.4-mini | 17-4 6 ties |
+0.19 | +19% | -$1.0606 | +14m 40s | +5.85 |
| opencode/gpt-5.4-nano | 10-14 3 ties |
-0.174 | -19% | -$0.4215 | +8m 56s | +0.21 |
| opencode/kimi-k2.5 | 14-12 1 ties |
-0.169 | -22% | -$0.9122 | -4m 36s | +1.14 |
| opencode/minimax-m2.5 | 15-6 6 ties |
+0.134 | +11% | -$0.6413 | +4m 13s | -3.48 |
| opencode/glm-5.1 | 17-6 4 ties |
+0.068 | +0% | -$1.8816 | -28m 11s | +3.33 |
| opencode/claude-opus-4-6 | 18-7 2 ties |
-0.055 | -22% | -$21.8757 | -3m 36s | +0.51 |
| opencode/claude-sonnet-4-6 | 18-5 4 ties |
+0.022 | -11% | -$11.8406 | -6m 02s | -1.04 |
| opencode/glm-5 | 18-5 4 ties |
-0.008 | -11% | -$6.4339 | +16m 18s | +3.82 |
| opencode/gpt-5.4 | 18-6 3 ties |
+0.006 | -11% | -$8.9827 | +3m 41s | +4.39 |
The benchmark result only matters in context: this section pairs the observed benchmark outcome with the catalog metadata and operating characteristics behind it.
No trustworthy automatic pricing reference found yet, so cost is currently unknown.